© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208557
    Prev
    Next
    INDEX
    Explanations

    bisecting or dividing

    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_25_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
     динами
    0.41
     WELL
    0.39
    लेट
    0.39
    Nu
    0.38
    Powerful
    0.38
    마
    0.38
     המ
    0.37
     ތ
    0.37
     강력
    0.37
    には
    0.37
    POSITIVE LOGITS
     poslední
    0.41
     Sì
    0.41
     etiology
    0.38
    associated
    0.38
     asociación
    0.38
     singly
    0.38
    tien
    0.38
    accompan
    0.38
    কারণ
    0.38
    امی
    0.37
    Activations Density 0.000%

    No Known Activations