© 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. 11695
    Prev
    Next
    INDEX
    Explanations

    clusters of capitalized words, especially names

    oai_token-act-pair · gemini-2.0-flash

    character names

    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
    ThroughAttribute
    -0.66
    舺
    -0.54
     الحره
    -0.53
    rophore
    -0.52
    tidase
    -0.52
    ngth
    -0.50
     FetchType
    -0.49
     muualla
    -0.49
    Explicación
    -0.49
     xlink
    -0.48
    POSITIVE LOGITS
    openConnection
    0.52
     endblock
    0.51
     plainte
    0.47
     giustizia
    0.46
    sellors
    0.46
    migrationBuilder
    0.46
     commerciali
    0.45
     usta
    0.45
     morire
    0.45
    protoc
    0.44
    Activations Density 1.576%

    No Known Activations