Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6029
    Prev
    Next
    INDEX
    Explanations

    text describing the features of a specific model of car, particularly Hemis and Cudas

    oai_token-act-pair · gemini-2.0-flash

    non-English words or phrases

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

    Plymouth Barracuda cars

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.67
    GraphicsUnit
    -0.61
    ✨:
    -0.60
    InputBorder
    -0.60
    Portail
    -0.60
    ImageContext
    -0.59
    AnchorStyles
    -0.58
    SourceChecksum
    -0.58
    Hentet
    -0.57
     '\\;'
    -0.57
    POSITIVE LOGITS
    بيرة
    0.51
     Feu
    0.49
    ěst
    0.48
     Baer
    0.48
     hinaus
    0.47
    مصادر
    0.46
     Vert
    0.46
    rights
    0.45
     بتاريخ
    0.45
    onesa
    0.44
    Activations Density 0.407%

    No Known Activations