© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141945
    Prev
    Next
    INDEX
    Explanations

    B words

    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_46_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
     trava
    0.45
     tirer
    0.40
    गराज
    0.39
     Отече
    0.39
     متحدہ
    0.39
    酤
    0.38
     नेपाल
    0.38
     अवलंब
    0.38
     स्वर्
    0.38
    Elater
    0.37
    POSITIVE LOGITS
     mock
    0.44
    markdown
    0.39
     imaginary
    0.39
    망
    0.39
    ñana
    0.38
     everything
    0.38
    품
    0.38
     itemprop
    0.37
    ressing
    0.37
    ipio
    0.37
    Activations Density 0.000%

    No Known Activations