© 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. 10830
    Prev
    Next
    INDEX
    Explanations

    the tokens "at" and "ure", sometimes followed by "tern"

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical text

    np_max-act · gemini-2.0-flash

    at

    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
     فريبيس
    -0.84
    脚注の使い方
    -0.84
    ModelAdmin
    -0.81
     Tect
    -0.72
     ModelRenderer
    -0.69
    enumi
    -0.68
    __(/*!
    -0.67
     diversify
    -0.67
     defaultstate
    -0.66
     utafitiHapana
    -0.66
    POSITIVE LOGITS
    ）」
    0.49
    pot
    0.48
    пада
    0.47
     pat
    0.47
    POT
    0.46
    팟
    0.45
    '
    0.45
     voll
    0.45
    "
    0.44
     pot
    0.43
    Activations Density 0.305%

    No Known Activations