© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4320
    Prev
    Next
    INDEX
    Explanations

    find in code

    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_39_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
     représentant
    0.41
     knowing
    0.39
     shutters
    0.38
     Bare
    0.37
     Llam
    0.36
     representando
    0.36
    扒
    0.36
    Rectangle
    0.36
     currents
    0.35
     grieving
    0.35
    POSITIVE LOGITS
    find
    0.53
     find
    0.52
     FIND
    0.45
    FIND
    0.44
     Find
    0.44
     پیدا
    0.43
     Finds
    0.42
    症
    0.42
    找到
    0.41
    icc
    0.40
    Activations Density 0.018%

    No Known Activations