© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36212
    Prev
    Next
    INDEX
    Explanations

    which means

    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_11_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
    ্ব
    0.59
    یز
    0.59
    www
    0.56
    -
    0.55
    this
    0.54
     ל
    0.54
     luminosity
    0.53
    ți
    0.52
     қ
    0.52
    ="
    0.52
    POSITIVE LOGITS
     offences
    0.70
     plantings
    0.66
     florals
    0.66
     convulsions
    0.65
    лис
    0.65
     injuries
    0.63
     discs
    0.63
     ditches
    0.63
     Ameri
    0.63
     toilets
    0.63
    Activations Density 0.012%

    No Known Activations