© 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. 258158
    Prev
    Next
    INDEX
    Explanations

    as much or as little

    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
    venture
    0.46
    विरुद्ध
    0.43
     जरूर
    0.42
    winning
    0.38
    ventures
    0.38
    vis
    0.37
    んばんは
    0.37
     顔
    0.37
    Leng
    0.37
    ADESH
    0.36
    POSITIVE LOGITS
     alto
    0.45
     Libra
    0.44
     orbital
    0.42
     largo
    0.39
     ternary
    0.39
     Alto
    0.39
     converge
    0.38
     depicted
    0.38
     consensus
    0.38
    মল
    0.38
    Activations Density 0.000%

    No Known Activations