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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8118
    Prev
    Next
    INDEX
    Explanations

    technical or legal documents, scientific papers, or fictional stories

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical texts

    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
    MemoryWarning
    -0.66
    featureID
    -0.65
    fillType
    -0.62
     незавершена
    -0.62
    denly
    -0.62
    ICEF
    -0.61
    migrationBuilder
    -0.61
    arithmic
    -0.60
    ousand
    -0.60
    CloseOperation
    -0.59
    POSITIVE LOGITS
    e
    1.98
    t
    1.63
    a
    1.62
    n
    1.60
    m
    1.54
    d
    1.49
    i
    1.43
    c
    1.43
    z
    1.41
    h
    1.40
    Activations Density 49.649%

    No Known Activations