© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219272
    Prev
    Next
    INDEX
    Explanations

    stand

    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_47_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
    ča
    0.44
    rpt
    0.41
     fairly
    0.38
     staring
    0.38
     stared
    0.38
    富
    0.37
     συνα
    0.37
     enth
    0.36
    Staff
    0.36
     Rich
    0.36
    POSITIVE LOGITS
    illerie
    0.43
    acteur
    0.38
    ლებელია
    0.37
    ObjectIndex
    0.37
    OSO
    0.37
    RefIn
    0.36
    㳑
    0.36
    ieux
    0.36
    ielo
    0.35
    䄳
    0.35
    Activations Density 0.001%

    No Known Activations