© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10830
    Prev
    Next
    INDEX
    Explanations

    viewpoints, facts, and feelings presented from the first person perspective

    oai_token-act-pair · gemini-2.0-flash

    Quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    InitVars
    -0.63
    ariado
    -0.60
     <<<<<<<<<<<<<<
    -0.54
    migrationBuilder
    -0.51
     terapi
    -0.49
    óngase
    -0.48
     ComVisible
    -0.48
     IndexPath
    -0.47
     Palatine
    -0.46
    loroethene
    -0.46
    POSITIVE LOGITS
     ویکی‌پدیا
    0.69
     propOrder
    0.67
     [*]
    0.66
     pinulongan
    0.58
    下载附件
    0.57
    WebElementEntity
    0.57
     nakalista
    0.56
    kloped
    0.56
     unknownFields
    0.56
    RepeatedField
    0.53
    Activations Density 7.140%

    No Known Activations