© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40212
    Prev
    Next
    INDEX
    Explanations

    just what

    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_11_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
     time
    0.47
     *
    0.47
     yea
    0.46
     চেয়ে
    0.46
    ilize
    0.46
    *,
    0.46
    arları
    0.46
    achron
    0.45
    eyim
    0.45
     ,
    0.44
    POSITIVE LOGITS
    ing
    0.53
    िंग
    0.53
     espí
    0.52
    州
    0.52
     imigr
    0.52
    GUARD
    0.51
    এটি
    0.50
     mobili
    0.50
    urón
    0.50
     attaques
    0.50
    Activations Density 0.018%

    No Known Activations