© 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
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105937
    Prev
    Next
    INDEX
    Explanations

    check-ins

    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_1_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
    ش
    1.10
    ิง
    1.01
    ิ
    1.00
    ى
    0.98
    اني
    0.93
    ীবনী
    0.93
     klik
    0.89
     a
    0.89
     ka
    0.87
    €™
    0.85
    POSITIVE LOGITS
    و
    1.95
    ו
    1.69
    2
    1.32
    ul
    1.20
    1
    1.17
    ה
    1.17
    კ
    1.16
    quele
    1.15
    the
    1.13
    sembling
    1.13
    Activations Density 0.001%

    No Known Activations