© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76096
    Prev
    Next
    INDEX
    Explanations

    variable data

    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_31_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
     ရက်
    0.35
    resses
    0.32
     utilising
    0.32
     ]))
    0.31
     resurrect
    0.31
     scegli
    0.30
    oraj
    0.30
     ಸಾ
    0.30
     различные
    0.30
     regiones
    0.30
    POSITIVE LOGITS
    comodule
    0.31
    FCO
    0.29
    Party
    0.29
    Î
    0.28
    Incremental
    0.27
    Mâ
    0.26
    단
    0.26
    voiced
    0.26
    Teddy
    0.25
    Comedy
    0.25
    Activations Density 0.000%

    No Known Activations