© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199554
    Prev
    Next
    INDEX
    Explanations

    GL

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ياء
    0.41
    )<-
    0.40
    inda
    0.39
     mes
    0.37
    ્યો
    0.37
    镗
    0.37
    溼
    0.37
    cn
    0.36
    Indiana
    0.36
    یاء
    0.36
    POSITIVE LOGITS
     POSSIBILITY
    0.49
    することも
    0.43
    بلغ
    0.42
    擇
    0.42
    择
    0.41
    uhl
    0.41
     posibilidad
    0.41
    poss
    0.40
    JI
    0.39
     Poss
    0.38
    Activations Density 0.001%

    No Known Activations