© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198623
    Prev
    Next
    INDEX
    Explanations

    equals add

    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_9_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
    in
    0.89
    л
    0.66
    尌
    0.63
    us
    0.61
    Y
    0.59
    ת
    0.58
    ل
    0.57
    it
    0.57
     κάνει
    0.56
    㔯
    0.56
    POSITIVE LOGITS
     is
    0.70
     ouvert
    0.57
     and
    0.55
     with
    0.55
     Installation
    0.53
     senc
    0.53
     applic
    0.53
     couches
    0.53
     irrever
    0.51
    έ
    0.50
    Activations Density 0.000%

    No Known Activations