© 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. 2023
    Prev
    Next
    INDEX
    Explanations

    sentences that describe a person's achievements in sports

    oai_token-act-pair · gemini-2.0-flash

    winning competitions

    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
     win
    -0.77
    win
    -0.68
     ISNI
    -0.63
     winning
    -0.58
    مصادر
    -0.55
    Geplaatst
    -0.53
    WIN
    -0.52
     AspNetCore
    -0.51
     earn
    -0.51
    Win
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.65
    protoimpl
    0.56
     GenerationType
    0.54
     aéro
    0.54
     périph
    0.52
    AddHtmlAttribute
    0.51
     tatouage
    0.50
    enumii
    0.50
    PreExecute
    0.49
    wahati
    0.47
    Activations Density 6.487%

    No Known Activations