© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29855
    Prev
    Next
    INDEX
    Explanations

    character name, technical report, calibration records

    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_40_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
    ụy
    0.39
     grand
    0.38
    šta
    0.37
    လျ
    0.37
    ၀၀
    0.36
    चूर
    0.36
    ⌒
    0.35
     orient
    0.34
    OMIC
    0.34
     `'\\
    0.34
    POSITIVE LOGITS
     card
    2.06
     कार्ड
    1.84
    カード
    1.84
     Card
    1.81
     cards
    1.77
    Card
    1.77
    card
    1.73
     কার্ড
    1.70
     카드
    1.67
    카드
    1.58
    Activations Density 0.108%

    No Known Activations