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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5927
    Prev
    Next
    INDEX
    Explanations

    positive sentiment expressing encouragement or emotional connection

    oai_token-act-pair · gemini-2.0-flash

    concepts related to spirituality or faith

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

    Lacking resources or capabilities

    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
    Gön
    -0.60
    ngdoc
    -0.57
    ApiOperation
    -0.53
     FetchType
    -0.50
     оригіналу
    -0.48
     distanciation
    -0.48
     Vikipedi
    -0.48
    migrationBuilder
    -0.47
     linked
    -0.45
    因为它
    -0.45
    POSITIVE LOGITS
     الحره
    0.57
     modesty
    0.56
     realism
    0.54
     humility
    0.54
     spirituality
    0.53
    richTextPanel
    0.53
    Mojo
    0.52
    érias
    0.51
     faith
    0.49
     airway
    0.49
    Activations Density 1.447%

    No Known Activations