© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215938
    Prev
    Next
    INDEX
    Explanations

    study by

    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_31_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
    ımız
    0.35
     mūsų
    0.35
    ánk
    0.34
    .$(
    0.33
     including
    0.33
     naš
    0.32
     smatra
    0.32
     שלנו
    0.32
     ყველ
    0.32
     완전
    0.32
    POSITIVE LOGITS
    Routed
    0.37
    ﮑ
    0.33
    vég
    0.33
     âge
    0.33
     slipper
    0.32
    iseach
    0.32
    тент
    0.31
    ceau
    0.31
    Sear
    0.31
     regimen
    0.31
    Activations Density 0.000%

    No Known Activations