© 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. 14616
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with scientific studies and reports

    oai_token-act-pair · gemini-2.0-flash

    Tests and evaluations

    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
     calculated
    -0.68
     Calculated
    -0.66
     evaluated
    -0.65
    calculated
    -0.63
    EVALUATION
    -0.62
     assessed
    -0.58
    Calculation
    -0.58
     evaluate
    -0.58
     Berechnung
    -0.58
     thorough
    -0.57
    POSITIVE LOGITS
     Roskov
    0.71
     lenker
    0.63
     Paglinawan
    0.62
     referenties
    0.61
     indisponible
    0.57
     Baillargeon
    0.57
    Бахар
    0.54
    GeoNames
    0.53
     Мексичка
    0.52
    principalColumn
    0.52
    Activations Density 11.430%

    No Known Activations