© 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. 8579
    Prev
    Next
    INDEX
    Explanations

    pronouns and conjunctions, often within sentences describing actions or events

    oai_token-act-pair · gemini-2.0-flash

    Narrative text

    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
     Board
    -0.52
    Datuak
    -0.51
     board
    -0.49
     BOARD
    -0.49
    ague
    -0.46
    ATURE
    -0.45
    JoinTable
    -0.44
    Board
    -0.44
     Drift
    -0.43
    gola
    -0.42
    POSITIVE LOGITS
     AssemblyProduct
    0.69
    expandindo
    0.69
    DataAnnotations
    0.68
    pyrene
    0.64
    ArgsConstructor
    0.63
    NOPQRST
    0.62
    IBarButtonItem
    0.60
    Билгалдахарш
    0.59
    complexContent
    0.59
    millimeters
    0.58
    Activations Density 2.419%

    No Known Activations