© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203930
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     servicios
    0.39
     Strukturen
    0.38
     সর্বনিম্ন
    0.38
     sistemas
    0.37
     seroton
    0.37
    allist
    0.37
     উপকার
    0.37
     _$_
    0.37
     linkages
    0.37
     частини
    0.37
    POSITIVE LOGITS
    type
    0.47
    lit
    0.46
    litre
    0.43
    eh
    0.39
    subs
    0.38
     type
    0.37
    px
    0.36
    lat
    0.36
    类型
    0.36
     Tribun
    0.36
    Activations Density 0.001%

    No Known Activations