© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13919
    Prev
    Next
    INDEX
    Explanations

    code and legal text fragments

    oai_token-act-pair · gemini-2.0-flash

    code and technical discussions

    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
     let
    -2.89
     Let
    -2.69
    let
    -2.59
     lets
    -2.53
    Let
    -2.52
     LET
    -2.39
     letting
    -2.38
     Lets
    -2.34
    Lets
    -2.25
    lets
    -2.19
    POSITIVE LOGITS
     snippetHide
    0.93
     autorytatywna
    0.92
    +#+
    0.91
    expandindo
    0.88
    Hochspringen
    0.83
     дописавши
    0.83
     تضيفلها
    0.80
    aarrggbb
    0.78
     myſelf
    0.76
    +#+#
    0.75
    Activations Density 1.650%

    No Known Activations