© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107977
    Prev
    Next
    INDEX
    Explanations

    each followed by noun

    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_1_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
    ী
    1.42
    ală
    1.24
    ו
    1.20
    સ
    1.16
    ق
    1.16
    ק
    1.15
    이었
    1.12
     üç
    1.09
    ს
    1.09
    ని
    1.09
    POSITIVE LOGITS
     for
    1.17
    AN
    1.15
    2
    1.02
    ada
    1.01
    il
    0.97
    eng
    0.96
    。
    0.96
    AL
    0.94
     in
    0.93
      
    0.93
    Activations Density 0.000%

    No Known Activations