© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12949
    Prev
    Next
    INDEX
    Explanations

    words that are part of or introduce quoted speech

    oai_token-act-pair · gemini-2.0-flash

    Code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    :✨
    -0.65
    rungsseite
    -0.65
    InitVars
    -0.64
     bad
    -0.63
     للاسماء
    -0.59
    verifyException
    -0.57
     BAD
    -0.57
     seo
    -0.57
    脚注の使い方
    -0.57
    Personensuche
    -0.56
    POSITIVE LOGITS
    **
    0.58
    SqlClient
    0.57
    /
    0.53
    .**
    0.52
    netbeans
    0.52
    1
    0.50
    rinfo
    0.49
     **
    0.49
    igshid
    0.49
    ServletException
    0.49
    Activations Density 2.052%

    No Known Activations