© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10587
    Prev
    Next
    INDEX
    Explanations

    mentions of points or scoring

    oai_token-act-pair · gemini-2.0-flash

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    tagHelperRunner
    -0.93
    :✨
    -0.86
    +:+
    -0.77
    Hochspringen
    -0.77
    pexpr
    -0.75
    Hozzáférés
    -0.75
     CreateTagHelper
    -0.75
    cheinend
    -0.73
     EconPapers
    -0.73
    abestanden
    -0.73
    POSITIVE LOGITS
     were
    0.50
     was
    0.49
     killed
    0.47
     خانگی
    0.43
     came
    0.43
     Championship
    0.42
    vencia
    0.40
     drove
    0.40
     drown
    0.40
     he
    0.40
    Activations Density 0.030%

    No Known Activations