© 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. 45936
    Prev
    Next
    INDEX
    Explanations

    dictionary items iteration

    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
    😛
    0.46
    pekt
    0.43
     computerChoice
    0.42
    ment
    0.40
     playerCount
    0.40
    ර්ථ
    0.39
     branchNode
    0.38
    কর্
    0.38
     পণ্ডিত
    0.38
    ())->
    0.38
    POSITIVE LOGITS
     Religion
    0.40
     buildings
    0.39
     Animal
    0.39
    тами
    0.39
     ро
    0.38
    జయ
    0.38
    सीसीआई
    0.37
     চিঠি
    0.37
     которой
    0.37
     unveiled
    0.37
    Activations Density 0.002%

    No Known Activations