© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193812
    Prev
    Next
    INDEX
    Explanations

    as [low, high, few, much]

    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_27_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
     defended
    0.42
     defend
    0.39
    eworld
    0.39
    ০০০
    0.38
     weren
    0.38
    ewana
    0.38
    एलबी
    0.37
    鯖
    0.37
    sec
    0.36
     خپل
    0.36
    POSITIVE LOGITS
     sedimentation
    0.41
     inequ
    0.41
     spontaneity
    0.39
     heterogeneity
    0.38
     peculiarity
    0.37
     irregularity
    0.36
     condensation
    0.36
     sensitization
    0.36
     rupt
    0.35
     bor
    0.35
    Activations Density 0.001%

    No Known Activations