© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6378
    Prev
    Next
    INDEX
    Explanations

    Japanese language characters and words, especially those related to beginnings and returns.

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     
    -0.83
    ↵↵
    -0.78
    ↵
    -0.73
     (
    -0.72
     and
    -0.71
    .
    -0.71
     of
    -0.71
    -
    -0.71
    <eos>
    -0.68
     to
    -0.66
    POSITIVE LOGITS
    AndEndTag
    1.16
     étoient
    1.09
     مرئيه
    1.07
     ainfi
    1.02
     auffi
    1.02
    ^(@)
    1.01
     Anſ
    0.96
     تانيه
    0.96
     Theſe
    0.96
     avoient
    0.94
    Activations Density 0.228%

    No Known Activations