© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11803
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and words that look like URLs or paths or version numbers

    oai_token-act-pair · gemini-2.0-flash

    - /

    np_max-act-logits · gemini-2.0-flash

    hyphen or slash Method used: 1 — because max-activating tokens are "-" and "/"

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ling
    -0.81
    li
    -0.79
    le
    -0.77
    lie
    -0.75
    lo
    -0.75
    la
    -0.74
    liness
    -0.73
    lies
    -0.73
    les
    -0.72
    lised
    -0.72
    POSITIVE LOGITS
    her
    0.50
    h
    0.49
    hh
    0.47
    hts
    0.43
    hi
    0.41
    hots
    0.41
    hic
    0.40
    hru
    0.40
    ht
    0.40
    hér
    0.38
    Activations Density 11.360%

    No Known Activations