© 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. 4158
    Prev
    Next
    INDEX
    Explanations

    measurements, machines, and companies

    oai_token-act-pair · gemini-2.0-flash

    Companies/chemical products

    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
    LookAnd
    -0.87
    MigrationBuilder
    -0.85
    fjspx
    -0.79
     NSCoder
    -0.77
    XmlAccessorType
    -0.75
    ⓧ
    -0.75
     للاسماء
    -0.74
    featureID
    -0.73
     noDo
    -0.73
    AddHtmlAttribute
    -0.72
    POSITIVE LOGITS
     Teknologi
    0.40
    ssysteme
    0.40
     COMMERCE
    0.39
    styrelsen
    0.38
     verdi
    0.37
    Jalan
    0.37
     kanak
    0.37
     Lugano
    0.36
    köz
    0.36
     Centrum
    0.35
    Activations Density 8.032%

    No Known Activations