© 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. 215832
    Prev
    Next
    INDEX
    Explanations

    column followed by value or time

    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
    apatos
    0.38
    verkehr
    0.37
     очередной
    0.36
    wiz
    0.36
     diciembre
    0.36
    浓
    0.35
    Choisissez
    0.35
     Monthly
    0.34
    Cron
    0.34
    amentul
    0.34
    POSITIVE LOGITS
     universality
    0.39
     topology
    0.38
     wytr
    0.37
     grafting
    0.37
     ultrasound
    0.36
     samud
    0.36
     physiotherapy
    0.36
    虧
    0.35
     Nang
    0.35
     fibres
    0.34
    Activations Density 0.005%

    No Known Activations