© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10749
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical manipulation using tools and materials

    oai_token-act-pair · gemini-2.0-flash

    crafts and assembling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     ModelExpression
    -0.96
    MigrationBuilder
    -0.83
     disparu
    -0.76
     mourir
    -0.75
     élevées
    -0.72
     brancas
    -0.70
     Administrativna
    -0.69
     InputDecoration
    -0.68
     AttributeSet
    -0.67
     privées
    -0.67
    POSITIVE LOGITS
     lenker
    0.50
    RTEX
    0.46
     constru
    0.44
     समीक्षक
    0.43
    adaptiveStyles
    0.43
     construction
    0.42
     Tink
    0.42
     TUL
    0.42
    emb
    0.41
     t
    0.40
    Activations Density 1.899%

    No Known Activations