© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12485
    Prev
    Next
    INDEX
    Explanations

    terms related to computer performance and system monitoring

    oai_token-act-pair · gemini-2.0-flash

    performance metrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    WriteLiteral
    -0.75
    erà
    -0.60
    vett
    -0.56
    alha
    -0.56
    olved
    -0.54
     vulgaires
    -0.54
    mara
    -0.54
    uska
    -0.52
    Glitch
    -0.50
    मर
    -0.50
    POSITIVE LOGITS
    ⓧ
    0.65
     Vikipedi
    0.64
    RenderAtEndOf
    0.63
    ">/
    0.59
     Strava
    0.58
     benchmarking
    0.56
     Carthag
    0.54
    UnknownFields
    0.54
    principalColumn
    0.52
     kulak
    0.52
    Activations Density 1.365%

    No Known Activations