© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227930
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    𝜁
    0.89
     refug
    0.88
    ０
    0.88
    𝜌
    0.88
     теат
    0.86
     ovar
    0.86
    ות
    0.85
     litros
    0.85
     кораб
    0.82
     analges
    0.81
    POSITIVE LOGITS
    un
    1.29
    p
    1.17
    re
    1.04
    ac
    1.04
    ach
    1.02
    her
    0.96
    z
    0.95
    em
    0.94
    ad
    0.93
    ib
    0.93
    Activations Density 0.000%

    No Known Activations