© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56635
    Prev
    Next
    INDEX
    Explanations

    damage and wind

    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_11_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
    立体
    0.52
    am
    0.51
    izowane
    0.47
     extremadamente
    0.46
    ленно
    0.46
     السيارات
    0.46
    碚
    0.46
     Model
    0.45
     Montag
    0.44
    of
    0.44
    POSITIVE LOGITS
    0.54
     кількість
    0.54
    ଛି
    0.53
     змін
    0.52
    ulitan
    0.51
    нэ
    0.51
     affirme
    0.50
     accred
    0.50
     بولی
    0.49
     inquis
    0.48
    Activations Density 0.034%

    No Known Activations