© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14220
    Prev
    Next
    INDEX
    Explanations

    text that seems to be from a game analysis or sports report

    oai_token-act-pair · gemini-2.0-flash

    unique identifiers or specific formatting patterns

    np_token-act-pair-logits · gpt-4o-mini

    Sports analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ftagPool
    -0.54
    хьтан
    -0.53
    freopen
    -0.52
    تفصیلات
    -0.51
     bağlantılar
    -0.45
    BeginContext
    -0.44
    twimg
    -0.43
     विश्वसनीयता
    -0.43
    resave
    -0.42
    joen
    -0.41
    POSITIVE LOGITS
    +#+#
    0.68
    ISupport
    0.65
     htmlFor
    0.64
    ❹
    0.63
    LookAnd
    0.60
     dome
    0.59
     Inflate
    0.57
    windowFixed
    0.56
     octa
    0.55
     wrinkle
    0.55
    Activations Density 1.615%

    No Known Activations