© 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. 7421
    Prev
    Next
    INDEX
    Explanations

    a mix of chemical terms, citations, place names with "Am", and verbs that indicate emotional arousal or forming a political group.

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    np_max-act-logits · gemini-2.0-flash
    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
     myſelf
    -1.55
     Efq
    -1.52
    tvguidetime
    -1.49
     متعلقه
    -1.46
    ſelf
    -1.46
     surla
    -1.45
     ―――――
    -1.42
     itſelf
    -1.42
    ValueStyle
    -1.41
     étoient
    -1.41
    POSITIVE LOGITS
     
    0.73
    ↵↵
    0.72
    .
    0.71
    <eos>
    0.70
    ↵
    0.69
    ,
    0.69
     (
    0.68
    -
    0.68
    1
    0.65
     in
    0.65
    Activations Density 11.052%

    No Known Activations