© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45733
    Prev
    Next
    INDEX
    Explanations

    he followed by has or 's

    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_22_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
    וח
    0.23
     nadi
    0.21
     Orrell
    0.21
     dici
    0.20
    Ка
    0.19
     hood
    0.19
     istnie
    0.19
    །
    0.19
    Hood
    0.19
     saraf
    0.19
    POSITIVE LOGITS
     வெளியிட்டு
    0.24
    othermic
    0.23
     criminality
    0.23
     दहशत
    0.21
     anguish
    0.21
    ეგის
    0.21
     আতঙ্ক
    0.21
    のかもし
    0.21
     Belediyesi
    0.20
    isinin
    0.20
    Activations Density 0.002%

    No Known Activations