© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78291
    Prev
    Next
    INDEX
    Explanations

    say "\n" characters

    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_53_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
     Thorough
    0.42
     thorough
    0.37
     dearly
    0.35
     ech
    0.35
     de
    0.34
     Des
    0.34
    endela
    0.34
    ս
    0.34
    tség
    0.34
     gesture
    0.33
    POSITIVE LOGITS
    -__
    0.37
    Ivo
    0.34
    дяки
    0.34
     आईपीएस
    0.34
     Feuilles
    0.33
    Oliver
    0.33
    .>
    0.33
    วัสดี
    0.32
     फोटोज
    0.32
    𝑋
    0.32
    Activations Density 0.005%

    No Known Activations