© 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. 206283
    Prev
    Next
    INDEX
    Explanations

    An error occurred

    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
    рово
    0.37
    もら
    0.36
    ประสบ
    0.36
    埄
    0.36
     أثناء
    0.35
    НГ
    0.35
     postures
    0.35
     setValue
    0.35
    ﾓ
    0.34
    abulary
    0.34
    POSITIVE LOGITS
    necessary
    0.56
     necessario
    0.51
     szükséges
    0.51
     necessary
    0.50
     necessário
    0.50
     nécessaire
    0.50
     necessária
    0.50
     necesarias
    0.49
     необходи
    0.49
     necesaria
    0.48
    Activations Density 0.003%

    No Known Activations