© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 36839
    Prev
    Next
    INDEX
    Explanations

    person's full name and attribution

    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_3_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
    in
    0.71
    ਮ
    0.70
     உயரம்
    0.65
     வெப்சீரி
    0.63
    ork
    0.63
    getPassword
    0.63
     ማስ
    0.61
    お金
    0.60
    oc
    0.59
    BG
    0.59
    POSITIVE LOGITS
     of
    0.72
     on
    0.66
    (
    0.62
    ল
    0.59
    م
    0.56
    链
    0.56
    <0xA8>
    0.54
    ट
    0.54
    зирован
    0.53
    ról
    0.52
    Activations Density 0.000%

    No Known Activations