© 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. 14580
    Prev
    Next
    INDEX
    Explanations

    words or prefixes related to a time period, often hyphenated

    oai_token-act-pair · gemini-2.0-flash

    monetary symbols or prefixes

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

    prefixes

    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
    verhält
    -0.60
    ără
    -0.60
    vaar
    -0.60
    losigkeit
    -0.59
    kammer
    -0.58
    vermögen
    -0.57
    staden
    -0.56
    fläche
    -0.56
    barkeit
    -0.55
    mitglied
    -0.54
    POSITIVE LOGITS
    -
    1.55
    -#
    0.93
    -$
    0.93
    -£
    0.92
    -'
    0.91
    -​
    0.89
    -%
    0.85
    -"
    0.83
    -“
    0.82
    $-
    0.79
    Activations Density 1.985%

    No Known Activations