© 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. 11526
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode notation

    oai_token-act-pair · gemini-2.0-flash

    $

    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
     Efq
    -1.97
     myſelf
    -1.88
     ―――――
    -1.75
     Monfieur
    -1.75
    NUMX
    -1.74
     Theſe
    -1.72
     itſelf
    -1.68
     Reſ
    -1.65
    ſelf
    -1.64
     Jefus
    -1.64
    POSITIVE LOGITS
     
    0.70
    <eos>
    0.70
     (
    0.63
     =
    0.61
    .
    0.54
    ↵
    0.54
    ,
    0.54
    ↵↵
    0.52
     I
    0.47
    1
    0.46
    Activations Density 4.409%

    No Known Activations