© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43055
    Prev
    Next
    INDEX
    Explanations

    variable assignment or conditional checks

    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
     deceived
    0.39
    運
    0.38
     operacional
    0.38
    น์
    0.37
     vận
    0.37
    人員
    0.36
    жку
    0.35
     deceiving
    0.35
     disappoint
    0.34
     опера
    0.34
    POSITIVE LOGITS
     дерева
    0.44
    ression
    0.43
    ad
    0.40
     우
    0.38
    allery
    0.38
     arbres
    0.37
     repaso
    0.37
     वृक्ष
    0.36
    overs
    0.35
     trees
    0.35
    Activations Density 0.010%

    No Known Activations