© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242879
    Prev
    Next
    INDEX
    Explanations

    n =

    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_40_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
    崞
    0.40
    дун
    0.40
    intervention
    0.38
    ဒ
    0.38
    ₵
    0.38
    खास्त
    0.37
     Intervention
    0.37
    intervento
    0.37
    都在
    0.37
     rì
    0.35
    POSITIVE LOGITS
     take
    0.56
    take
    0.52
     prendre
    0.45
     takes
    0.42
     values
    0.40
    학
    0.40
     assign
    0.39
    ানা
    0.39
    取る
    0.39
    Take
    0.39
    Activations Density 0.006%

    No Known Activations