© 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. 40437
    Prev
    Next
    INDEX
    Explanations

    support allegations

    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
    れい
    0.55
    ように
    0.54
    
    0.53
    在庫
    0.53
    AK
    0.52
    と呼ば
    0.52
    ぐ
    0.52
     trattamento
    0.51
    MARTIN
    0.50
    ◑
    0.50
    POSITIVE LOGITS
    amic
    0.59
    ovy
    0.53
     enamel
    0.50
     فقد
    0.50
     Stony
    0.50
    <0x80>
    0.50
    agers
    0.50
     Clin
    0.49
    ট্রোল
    0.49
     যৌথ
    0.49
    Activations Density 0.006%

    No Known Activations