© 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. 11092
    Prev
    Next
    INDEX
    Explanations

    technical words and measurements related to engineering, physics, or testing.

    oai_token-act-pair · gemini-2.0-flash

    Measuring force

    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
     sau
    -0.57
    tvguidetime
    -0.54
    سطس
    -0.54
    덕
    -0.52
    kaufs
    -0.50
    argout
    -0.50
     Geografia
    -0.48
    edged
    -0.48
    hein
    -0.47
     gyhoeddwyd
    -0.47
    POSITIVE LOGITS
    migrationBuilder
    0.82
    CloseOperation
    0.67
    bootstrapcdn
    0.67
    AutoresizingMask
    0.67
     فريبيس
    0.65
    Atoi
    0.58
    TagMode
    0.56
     jsPsych
    0.55
     vivido
    0.54
    CopyWith
    0.53
    Activations Density 0.778%

    No Known Activations