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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133778
    Prev
    Next
    INDEX
    Explanations

    transient nature or populations

    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
    ה
    1.52
    י
    1.41
    ע
    1.39
    ש
    1.38
    ال
    1.32
    ه
    1.30
    ت
    1.27
    したので
    1.24
    ط
    1.20
    '
    1.15
    POSITIVE LOGITS
    I
    1.49
    Validator
    0.99
    tering
    0.95
    Dining
    0.95
    Maker
    0.93
    Event
    0.92
    Dropout
    0.92
    fer
    0.89
    Coefficient
    0.89
    Ticket
    0.88
    Activations Density 0.000%

    No Known Activations