© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1870
    Prev
    Next
    INDEX
    Explanations

    angle-bracket delimited XML-like data structures with "pcre" tags.

    oai_token-act-pair · gemini-2.0-flash

    code and logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Retrieve
    -0.69
     Register
    -0.69
     Restore
    -0.67
     Rewrite
    -0.67
    Register
    -0.66
     Get
    -0.66
     Create
    -0.66
     Donate
    -0.65
     Download
    -0.65
     Install
    -0.65
    POSITIVE LOGITS
     Years
    0.71
    المشاركات
    0.69
     Area
    0.69
     ويكيميديا
    0.68
     Period
    0.67
     Time
    0.66
     ComVisible
    0.65
     Kind
    0.65
     Thing
    0.64
    HtmlAttribute
    0.64
    Activations Density 6.875%

    No Known Activations