© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63349
    Prev
    Next
    INDEX
    Explanations

    city names and landmarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __);
    0.41
    Abasis
    0.41
    ಲೇ
    0.39
    𝔰
    0.38
    izer
    0.37
    izable
    0.36
    ização
    0.36
    ♧
    0.35
     antis
    0.35
     Compañ
    0.35
    POSITIVE LOGITS
    甸
    0.44
    逻
    0.42
    Georges
    0.41
     Georges
    0.40
    ებით
    0.40
    膻
    0.39
     космети
    0.39
    体内
    0.38
     DICK
    0.38
    ებული
    0.37
    Activations Density 0.011%

    No Known Activations