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. 11160
    Prev
    Next
    INDEX
    Explanations

    instructions for using a VPN

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or keywords

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

    Computer settings/options

    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
     surla
    -0.69
    geordnete
    -0.52
    protoc
    -0.51
    TagMode
    -0.51
    фраструк
    -0.51
     ब्रेकडाउन
    -0.51
    月号
    -0.49
    UnsafeEnabled
    -0.49
    rivit
    -0.49
    MIO
    -0.49
    POSITIVE LOGITS
    principalTable
    0.55
     Slo
    0.50
     Cort
    0.49
    XmlAccessorType
    0.48
    DebuggerStep
    0.48
    DoubleQuotes
    0.48
    fromnode
    0.47
    fjspx
    0.47
     Efq
    0.47
     uParam
    0.44
    Activations Density 1.749%

    No Known Activations