© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39488
    Prev
    Next
    INDEX
    Explanations

    model

    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_57_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
    沿
    0.42
    ೊಂಡ
    0.38
     tm
    0.37
    politik
    0.37
    XZ
    0.37
    zok
    0.37
    Along
    0.36
    angga
    0.35
    १
    0.35
    breath
    0.35
    POSITIVE LOGITS
     Dam
    0.40
     ringing
    0.39
    佾
    0.39
     look
    0.38
     बिफोर
    0.37
     damper
    0.37
     Juris
    0.37
    Look
    0.36
     fácilmente
    0.36
     Coh
    0.36
    Activations Density 0.000%

    No Known Activations