© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6306
    Prev
    Next
    INDEX
    Explanations

    the abstract concept of power

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to language or power

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

    power

    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
    MergeFrom
    -0.40
    疑
    -0.39
     piet
    -0.38
    ミナ
    -0.38
    gio
    -0.37
     мо
    -0.37
     ramo
    -0.36
     s
    -0.36
    koj
    -0.36
    ्रीय
    -0.35
    POSITIVE LOGITS
     للاسماء
    1.07
    InjectAttribute
    0.82
    IUrlHelper
    0.79
     AssemblyCulture
    0.78
    AutoField
    0.77
     houſe
    0.76
    EndInit
    0.73
     Shakspeare
    0.72
    extAlignment
    0.72
    tagHelperRunner
    0.72
    Activations Density 2.341%

    No Known Activations