© 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. 7979
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific publications

    oai_token-act-pair · gemini-2.0-flash

    result

    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
    Demografie
    -0.51
    UpInside
    -0.50
    llac
    -0.48
     चीज़ों
    -0.48
     кӀ
    -0.47
    NATIVE
    -0.47
    ybė
    -0.47
    CppCodeGen
    -0.46
    __':
    -0.46
    ssaint
    -0.46
    POSITIVE LOGITS
     result
    1.13
     Result
    1.08
    result
    1.05
    Result
    0.95
     RESULT
    0.90
     résultat
    0.89
     resultado
    0.83
     risultato
    0.79
     resultat
    0.74
    RESULT
    0.71
    Activations Density 9.829%

    No Known Activations