© 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. 1058
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is described as in some state of being

    oai_token-act-pair · gemini-2.0-flash

    are

    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
     ModelExpression
    -0.79
    findpost
    -0.79
    migrationBuilder
    -0.73
    AutoScaleMode
    -0.73
     AssemblyProduct
    -0.71
     insuffisamment
    -0.69
    ########.
    -0.68
     intptr
    -0.65
     SwiftUI
    -0.65
    complexContent
    -0.65
    POSITIVE LOGITS
    XmlAccessType
    0.60
    capri
    0.48
     casó
    0.47
    crown
    0.45
    molecular
    0.44
    quelize
    0.44
    ceased
    0.44
    PushButton
    0.43
    OrEmpty
    0.43
    menes
    0.43
    Activations Density 4.605%

    No Known Activations