© 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. 257980
    Prev
    Next
    INDEX
    Explanations

    Global Area, Buildings, Butch, tiered

    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
    z
    0.53
     anaerobic
    0.50
     victory
    0.48
     activists
    0.48
     viability
    0.48
    r
    0.47
     evening
    0.44
     whenever
    0.44
     kadar
    0.43
     sniper
    0.43
    POSITIVE LOGITS
    នោះ
    0.53
     Manche
    0.52
    闱
    0.51
    OMI
    0.49
    Lag
    0.49
     聞い
    0.49
    ಕ್ರಮ
    0.48
    érrez
    0.47
    嫔
    0.46
    𝙀
    0.46
    Activations Density 0.000%

    No Known Activations