© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12921
    Prev
    Next
    INDEX
    Explanations

    seemingly unrelated words in varied contexts, with a possible focus on data monitoring, professional roles, or peripheral details related to health/time.

    oai_token-act-pair · gemini-2.0-flash

    common words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AND
    -0.93
     oder
    -0.77
     eller
    -0.72
    或
    -0.69
     或
    -0.63
     یا
    -0.62
    Personensuche
    -0.62
     или
    -0.61
    und
    -0.60
     atau
    -0.60
    POSITIVE LOGITS
     and
    2.64
    jspx
    0.68
    حياته
    0.67
    Autoritní
    0.66
    性和
    0.65
    MessageInfo
    0.60
    리고
    0.60
    IContainer
    0.60
    +#+#
    0.59
    migrationBuilder
    0.58
    Activations Density 0.560%

    No Known Activations