© 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. 31221
    Prev
    Next
    INDEX
    Explanations

    out extensions

    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
    Yard
    0.27
    ADH
    0.27
     নীরব
    0.26
     diag
    0.26
     сне
    0.25
    🎄
    0.25
     stripe
    0.25
    🎃
    0.25
    Diag
    0.25
     cruc
    0.24
    POSITIVE LOGITS
     betting
    0.41
     bettors
    0.40
    Zhou
    0.36
     Betting
    0.35
     Zhou
    0.34
     gambling
    0.34
     Kalyan
    0.33
     Las
    0.33
     wagering
    0.33
    syair
    0.32
    Activations Density 0.000%

    No Known Activations