© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1488
    Prev
    Next
    INDEX
    Explanations

    uppercase character followed by "M"

    oai_token-act-pair · 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
    aarrggbb
    -0.81
    oredCriteria
    -0.75
    Vidite
    -0.73
     SIMBAD
    -0.72
     defaultstate
    -0.70
     useAppContext
    -0.69
    حوالہ
    -0.68
     itſelf
    -0.66
    iotensin
    -0.66
    Carriera
    -0.66
    POSITIVE LOGITS
    ATCH
    0.43
    ouse
    0.43
    ass
    0.42
    arti
    0.41
    atch
    0.40
    at
    0.40
    WebServlet
    0.40
    ob
    0.40
    ano
    0.38
    os
    0.38
    Activations Density 4.239%

    No Known Activations