© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78685
    Prev
    Next
    INDEX
    Explanations

    nutrients or locks

    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_0_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
    on
    1.72
    ت
    1.66
    ز
    1.65
    ن
    1.59
    ס
    1.56
    to
    1.45
    ל
    1.45
    ts
    1.44
    the
    1.44
    т
    1.44
    POSITIVE LOGITS
    '
    1.60
     hypothes
    1.23
    서
    1.23
     I
    1.19
     instrumentality
    1.16
    ۳
    1.12
    ak
    1.11
     idiosyncratic
    1.10
     sovereigns
    1.09
     chagrin
    1.05
    Activations Density 0.001%

    No Known Activations