© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2114
    Prev
    Next
    INDEX
    Explanations

    Okay, That

    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_40_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
    úncia
    0.36
    冦
    0.35
    itudinal
    0.33
    amment
    0.33
    ClientID
    0.33
    中心
    0.33
    centering
    0.32
    </em>
    0.32
    enu
    0.32
    opaedic
    0.32
    POSITIVE LOGITS
     stop
    0.44
     Stop
    0.44
    󠁣
    0.38
     Bi
    0.38
     গর্
    0.38
     недели
    0.37
     Without
    0.37
     Fist
    0.35
     বিনা
    0.35
     uden
    0.35
    Activations Density 0.107%

    No Known Activations