© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122564
    Prev
    Next
    INDEX
    Explanations

    listed on exchange

    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_37_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
    ܡܪ
    0.40
    Ẫ
    0.39
     disapp
    0.38
    經歷
    0.37
    作為
    0.35
    קד
    0.35
     periodically
    0.35
    氶
    0.35
     Lodge
    0.35
    ન્મ
    0.35
    POSITIVE LOGITS
     Snow
    0.39
     Num
    0.39
     האל
    0.39
     list
    0.39
    pointers
    0.38
     asos
    0.38
     собе
    0.37
     सुकून
    0.36
     tabla
    0.36
     cous
    0.36
    Activations Density 0.000%

    No Known Activations