© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13080
    Prev
    Next
    INDEX
    Explanations

    code snippets in what appears to be JSON or similar data serialization format

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    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
    R
    -1.50
    C
    -1.50
     R
    -1.45
     C
    -1.45
    G
    -1.44
     D
    -1.41
    F
    -1.41
    D
    -1.40
     G
    -1.38
    H
    -1.38
    POSITIVE LOGITS
     تضيفلها
    0.69
     RISERV
    0.66
     Kích
    0.63
     Wiktionnaire
    0.61
     HIEROGLYPH
    0.60
    MigrationBuilder
    0.60
    بوابة
    0.59
     AQUÍ
    0.58
     CONDU
    0.57
     CALIFORNI
    0.57
    Activations Density 27.816%

    No Known Activations