© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1948
    Prev
    Next
    INDEX
    Explanations

    technical writing in the field of electrical engineering or medical testing which involves physical apparatuses.

    oai_token-act-pair · gemini-2.0-flash

    specific technical terms or jargon

    np_token-act-pair-logits · gpt-4o-mini

    wires and needles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ISTAT
    -0.53
    avax
    -0.51
     AssemblyTitle
    -0.50
     صوتيه
    -0.49
    Lieferumfang
    -0.48
    NewRow
    -0.48
    liquez
    -0.48
    lineno
    -0.48
    subpackage
    -0.48
     كمان
    -0.47
    POSITIVE LOGITS
    WireFormatLite
    0.71
    IntoConstraints
    0.69
     يتيمه
    0.65
    fillType
    0.56
     stranded
    0.52
    tip
    0.52
    aarrggbb
    0.52
    Према
    0.52
    PerformLayout
    0.50
     tipped
    0.50
    Activations Density 1.495%

    No Known Activations