© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5912
    Prev
    Next
    INDEX
    Explanations

    questions and related question words, as well as words like "passion" and "what."

    oai_token-act-pair · gemini-2.0-flash

    what

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     nakalista
    -0.55
    Lähteet
    -0.52
    xxi
    -0.49
    redient
    -0.46
     hasten
    -0.46
    migrationBuilder
    -0.46
     sube
    -0.45
    +#+
    -0.45
    Rüyada
    -0.44
    anic
    -0.44
    POSITIVE LOGITS
     AttributeSet
    0.72
     виправивши
    0.69
    Décès
    0.68
    الحياه
    0.64
     HttpNotFound
    0.57
    GeneratedValue
    0.57
     Familienname
    0.57
    iecie
    0.57
     بيها
    0.55
    []{"
    0.55
    Activations Density 1.898%

    No Known Activations