© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    abbreviations and identifiers that look like model numbers

    oai_token-act-pair · gemini-2.0-flash

    foreign language terms or phrases

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

    chemical formulations

    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
     referenties
    -0.99
     transfieras
    -0.94
    Билгалдахарш
    -0.89
     ProtoMessage
    -0.88
    webElementXpaths
    -0.88
    bootstrapcdn
    -0.82
    +#+#
    -0.81
    UnsafeEnabled
    -0.79
    GeneratedCode
    -0.77
     mergeFrom
    -0.77
    POSITIVE LOGITS
     مواليد
    0.55
    Décès
    0.50
    itinéraire
    0.44
    IntoConstraints
    0.41
     despacho
    0.40
    asional
    0.37
     tượng
    0.37
    giar
    0.37
    AnimationsModule
    0.36
     étrangères
    0.36
    Activations Density 8.176%

    No Known Activations