© 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. 166746
    Prev
    Next
    INDEX
    Explanations

    plot or synopsis

    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
     FOREIGN
    0.36
     ます
    0.35
     ><
    0.35
    蔚
    0.35
    >\
    0.34
    くん
    0.34
    BIUM
    0.34
     emploi
    0.33
     பல்
    0.33
     overrun
    0.33
    POSITIVE LOGITS
    冊
    0.40
    Thin
    0.40
    Eyes
    0.39
    Sydney
    0.39
    Fract
    0.39
    Tue
    0.38
    menes
    0.38
     Sonata
    0.38
    투
    0.37
    Lavender
    0.37
    Activations Density 0.002%

    No Known Activations