© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 262021
    Prev
    Next
    INDEX
    Explanations

    sub-types and subdivisions

    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_22_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
    管控
    0.43
     PlayerSelector
    0.41
     ଜ
    0.41
    ertown
    0.40
    森
    0.39
    管理人
    0.39
    ग्राउंड
    0.39
    곁
    0.39
    वॉ
    0.39
     tulang
    0.38
    POSITIVE LOGITS
    десь
    0.44
     possibilidades
    0.40
     specifying
    0.40
     dizendo
    0.39
     aquarium
    0.38
     mentioning
    0.37
     proposing
    0.37
     aplicações
    0.37
     another
    0.37
     designating
    0.37
    Activations Density 0.006%

    No Known Activations