© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161036
    Prev
    Next
    INDEX
    Explanations

    практически без

    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_2_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
    ت
    1.52
    ي
    1.43
     endorsements
    1.33
    5
    1.31
    t
    1.30
     operands
    1.28
     molds
    1.25
     imperatives
    1.23
     odors
    1.20
     offences
    1.15
    POSITIVE LOGITS
    ä
    1.46
    ل
    1.45
    ре
    1.16
    ん
    1.13
    ang
    1.13
    ها
    1.12
    aría
    1.12
    util
    1.09
    ung
    1.08
    ia
    1.07
    Activations Density 0.000%

    No Known Activations