© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10978
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to the plotlines of stories and scientific studies.

    oai_token-act-pair · gemini-2.0-flash

    story or science

    np_max-act · gemini-2.0-flash

    say "▁" Method used: 2 — all following tokens start with the whitespace subtoken (▁), so say "▁"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdc
    -0.59
    ze
    -0.53
    windowFixed
    -0.49
    お楽しみに
    -0.47
     justru
    -0.47
    readInt
    -0.45
    rdı
    -0.45
    lagte
    -0.44
     remercie
    -0.44
     tiling
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.68
     فريبيس
    0.68
    ="@+
    0.66
     jspb
    0.66
     consultato
    0.66
     disambiguazione
    0.65
    astify
    0.63
    Спасылкі
    0.62
     CiNii
    0.57
    situation
    0.55
    Activations Density 1.515%

    No Known Activations