© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3475
    Prev
    Next
    INDEX
    Explanations

    the word "reasons."

    oai_token-act-pair · gemini-2.0-flash

    reasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     reasons
    -0.76
    KommentareTeilen
    -0.60
     peli
    -0.59
    sp
    -0.59
     Tafel
    -0.53
    FYI
    -0.52
    I
    -0.51
     onData
    -0.50
    AGE
    -0.49
     razones
    -0.49
    POSITIVE LOGITS
    TintMode
    0.83
     муніципалі
    0.77
    évaluateur
    0.73
    voorbeeld
    0.70
    chengladbach
    0.70
    })));
    0.65
    ształ
    0.65
    QMetaType
    0.65
     TextAppearance
    0.63
     rêver
    0.63
    Activations Density 1.482%

    No Known Activations