© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232374
    Prev
    Next
    INDEX
    Explanations

    repair or create

    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_32_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
     تعال
    0.38
    بك
    0.36
     सेवा
    0.36
    ionario
    0.36
    DetailsService
    0.36
    ப்படுகிறது
    0.35
    avalt
    0.35
    索
    0.35
     exp
    0.35
    Summar
    0.35
    POSITIVE LOGITS
     locomotion
    0.45
     chemotherapy
    0.37
     sanitary
    0.37
     Bathroom
    0.37
     contempt
    0.37
     cocon
    0.36
     supernatant
    0.36
    常
    0.36
     Cone
    0.35
     constant
    0.35
    Activations Density 0.001%

    No Known Activations