© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148326
    Prev
    Next
    INDEX
    Explanations

    charset=

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     biomass
    0.43
     chicken
    0.42
     obstruct
    0.42
     poultry
    0.41
     inflict
    0.41
    backpack
    0.39
     refurb
    0.38
    重複
    0.38
    ァ
    0.38
    isetas
    0.38
    POSITIVE LOGITS
    बिन
    0.44
    aye
    0.42
     personales
    0.42
     Vereinigte
    0.41
     entreprises
    0.40
    megaphone
    0.39
     tcpHeader
    0.39
    inning
    0.39
    ael
    0.39
    ColorEffects
    0.39
    Activations Density 0.000%

    No Known Activations