© 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. 12330
    Prev
    Next
    INDEX
    Explanations

    tabular data including numbers, percentages, and units of measure.

    oai_token-act-pair · 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
     guard
    -0.34
     drop
    -0.32
     coordinating
    -0.32
     Foote
    -0.31
     visualization
    -0.31
     cracking
    -0.31
     catch
    -0.31
    кто
    -0.31
     infec
    -0.31
     endeavor
    -0.31
    POSITIVE LOGITS
    bootstrapcdn
    0.98
    SharedDtor
    0.91
    ](#
    0.90
    archiviato
    0.88
     XNUMX
    0.88
    ScopeManager
    0.85
     tslint
    0.82
     referrerpolicy
    0.82
    UVWXYZ
    0.81
    NUMX
    0.81
    Activations Density 67.628%

    No Known Activations