© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1626
    Prev
    Next
    INDEX
    Explanations

    words that indicate the subject of the sentence is unusual, flawed, difficult, or an exception

    oai_token-act-pair · gemini-2.0-flash

    general text/articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     незавершена
    -0.76
     ſeveral
    -0.75
     resourceCulture
    -0.71
     itſelf
    -0.69
    +#+#
    -0.68
     myſelf
    -0.66
    abestanden
    -0.65
    horabuena
    -0.65
     Theſe
    -0.65
     enfans
    -0.63
    POSITIVE LOGITS
     Mr
    0.55
    iken
    0.51
     but
    0.51
    ies
    0.50
     mit
    0.50
     Dor
    0.49
    iri
    0.49
    TabIndex
    0.49
    cat
    0.48
     ||
    0.48
    Activations Density 10.793%

    No Known Activations