© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6658
    Prev
    Next
    INDEX
    Explanations

    the word "detection" or "detect"

    oai_token-act-pair · gemini-2.0-flash

    detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     дописавши
    -1.14
     himo
    -1.14
    httphttps
    -1.13
     unknownFields
    -1.13
    ividual
    -0.98
    oredCriteria
    -0.97
    ignty
    -0.94
    unately
    -0.94
     Italijanski
    -0.93
    complexContent
    -0.93
    POSITIVE LOGITS
    t
    0.64
    r
    0.61
     Poids
    0.60
     financiero
    0.57
    k
    0.56
     Patro
    0.56
    ing
    0.56
     accountable
    0.55
     trefoil
    0.55
     aikaa
    0.54
    Activations Density 1.668%

    No Known Activations