© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209462
    Prev
    Next
    INDEX
    Explanations

    letting

    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_10_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
     \
    0.66
     at
    0.64
     Arm
    0.59
     contemporaries
    0.59
     de
    0.55
     oxid
    0.55
    手間
    0.54
    愆
    0.54
     -
    0.54
     Auschwitz
    0.54
    POSITIVE LOGITS
    6
    0.72
    4
    0.70
    7
    0.66
    turn
    0.65
    ak
    0.64
    to
    0.64
    gun
    0.64
    transpose
    0.64
    ta
    0.63
    can
    0.63
    Activations Density 0.000%

    No Known Activations