© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7272
    Prev
    Next
    INDEX
    Explanations

    emotionally descriptive language, particularly when used to exaggerate or create a mood.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     highly
    -0.68
     consultato
    -0.62
     impressive
    -0.61
     tartalomajánló
    -0.60
     violent
    -0.60
     costly
    -0.59
     expansive
    -0.58
     attractive
    -0.57
     expensive
    -0.57
    migrationBuilder
    -0.57
    POSITIVE LOGITS
    وحة
    0.53
    InputTagHelper
    0.52
     weakness
    0.51
    MigrationBuilder
    0.49
    Slab
    0.49
    Ārējās
    0.49
    ForRow
    0.49
    JpaRepository
    0.47
     numbness
    0.47
    EndContext
    0.46
    Activations Density 2.881%

    No Known Activations