© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164795
    Prev
    Next
    INDEX
    Explanations

    here was/were/are

    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
     fug
    0.37
     polinom
    0.37
     explode
    0.35
    ْب
    0.35
     danse
    0.35
     होगा
    0.35
     furnish
    0.34
    妳
    0.33
    ank
    0.33
     Pau
    0.33
    POSITIVE LOGITS
     conditions
    0.37
     näher
    0.36
     particular
    0.35
    Specificity
    0.35
     widening
    0.34
    чники
    0.33
    鉾
    0.33
     conformity
    0.32
     unfolding
    0.31
    تری
    0.31
    Activations Density 0.001%

    No Known Activations