© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165226
    Prev
    Next
    INDEX
    Explanations

    temporarily disable or remove

    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_13_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
    et
    0.63
    hind
    0.57
    icolo
    0.56
    adem
    0.55
    farin
    0.55
     మాత్రమే
    0.54
    洴
    0.54
     ==
    0.53
    limited
    0.53
     Limited
    0.52
    POSITIVE LOGITS
     ምልክ
    0.50
    튼
    0.49
    ༸
    0.49
    ENS
    0.48
    Prototype
    0.47
     detectors
    0.47
    ts
    0.47
     practicality
    0.46
    TTY
    0.46
    TIMEOUT
    0.46
    Activations Density 0.003%

    No Known Activations