© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13963
    Prev
    Next
    INDEX
    Explanations

    text related to fire fighting activities and/or the symptoms, causes, and treatment of food poisoning.

    oai_token-act-pair · gemini-2.0-flash

    terms related to burns and poisoning

    np_token-act-pair-logits · gpt-4o-mini

    Injury, harm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    endpush
    -0.69
    脚注の使い方
    -0.63
    matchCondition
    -0.54
    kmal
    -0.52
     Score
    -0.52
     faldas
    -0.51
    ChildScrollView
    -0.50
     tartalomajánló
    -0.50
     capitales
    -0.49
    TagMode
    -0.47
    POSITIVE LOGITS
    parsedMessage
    0.71
     burns
    0.70
     bites
    0.64
    NOPQRST
    0.63
    burns
    0.63
     poisoning
    0.60
    ocardial
    0.60
     burn
    0.59
    bite
    0.59
    bites
    0.57
    Activations Density 1.980%

    No Known Activations