© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199467
    Prev
    Next
    INDEX
    Explanations

    chipmunk, virtue

    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_15_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
    </strong>
    0.57
    на
    0.57
    ජ
    0.54
    貥
    0.54
     mulher
    0.54
     gäller
    0.53
    ხილ
    0.53
    OpenJDK
    0.52
    ИА
    0.52
     Wikip
    0.52
    POSITIVE LOGITS
     divisions
    0.51
    ringe
    0.46
    l
    0.46
     turnover
    0.45
    റിൽ
    0.43
    line
    0.43
     rushing
    0.43
    ={`
    0.43
     सप्त
    0.43
    雑
    0.43
    Activations Density 0.000%

    No Known Activations