© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51024
    Prev
    Next
    INDEX
    Explanations

    inspect model weights

    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_30_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
     đêm
    0.35
    적
    0.34
     пя
    0.33
     тү
    0.32
    ix
    0.32
    がつ
    0.31
     താ
    0.31
     ký
    0.31
    град
    0.31
     название
    0.31
    POSITIVE LOGITS
    Driving
    0.37
    Bibitem
    0.36
    Benzo
    0.36
    NOP
    0.35
     unaltered
    0.35
    ンダ
    0.34
     শরণ
    0.33
     Soll
    0.33
    ड़ों
    0.33
    ndo
    0.33
    Activations Density 0.012%

    No Known Activations