© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31794
    Prev
    Next
    INDEX
    Explanations

    gall

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Ạ
    0.36
     Autof
    0.35
    ուն
    0.34
     punch
    0.33
    èbre
    0.33
    ernacle
    0.33
     caoutchouc
    0.33
    嘻
    0.33
    )$.
    0.32
     Accident
    0.32
    POSITIVE LOGITS
     gall
    2.33
    gall
    1.89
     Gall
    1.88
    Gall
    1.84
     GALL
    1.77
     g
    1.48
     gallbladder
    1.46
     galle
    1.40
    GALL
    1.38
     gallon
    1.23
    Activations Density 0.101%

    No Known Activations