© 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. 53932
    Prev
    Next
    INDEX
    Explanations

    links to css files

    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
    corto
    0.38
    turns
    0.37
    vred
    0.37
    turn
    0.37
    ➙
    0.36
    WaitFor
    0.36
    urre
    0.35
    擰
    0.35
    moves
    0.35
    transmitter
    0.35
    POSITIVE LOGITS
     signos
    0.43
     signes
    0.41
     countryside
    0.37
     Shill
    0.37
     Sophie
    0.36
     endings
    0.36
     signs
    0.36
     signage
    0.35
     இந்திய
    0.35
     செய்த
    0.35
    Activations Density 0.001%

    No Known Activations