© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4456
    Prev
    Next
    INDEX
    Explanations

    something unexpected

    oai_token-act-pair · gemini-2.0-flash

    negation/contrast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RenderAtEndOf
    -0.76
    AccessorTable
    -0.73
    expandindo
    -0.71
    protoimpl
    -0.69
    UnusedPrivate
    -0.66
    verwijspagina
    -0.65
    PasswordEncoder
    -0.64
    URLException
    -0.61
    ngrx
    -0.61
    存于互联网档案馆
    -0.60
    POSITIVE LOGITS
     falsos
    0.50
     falsa
    0.48
     voorbere
    0.46
     fausse
    0.43
    //
    0.42
     vorbereitet
    0.42
    ---
    0.41
    //--
    0.41
     falso
    0.41
    tekend
    0.40
    Activations Density 1.527%

    No Known Activations