© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27772
    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_40_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
    leukin
    0.42
     chill
    0.42
     pads
    0.40
    ega
    0.38
     Pads
    0.37
     highland
    0.36
    ̞
    0.35
    nere
    0.35
     Amn
    0.34
     Chill
    0.34
    POSITIVE LOGITS
    藩
    0.37
     Confederate
    0.34
    Blues
    0.33
    钡
    0.33
     सहा
    0.32
    垚
    0.32
     ਤੇ
    0.32
    بلی
    0.32
    ડો
    0.31
     Sabbath
    0.31
    Activations Density 0.014%

    No Known Activations