© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35245
    Prev
    Next
    INDEX
    Explanations

    using <ctrl63>

    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_31_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
    㨁
    0.47
     dissati
    0.40
    ヤモンド
    0.39
    সুমে
    0.38
     übernehmen
    0.38
     unhappiness
    0.37
     остальных
    0.36
     rencont
    0.36
     unsuccessful
    0.36
     фаразы
    0.36
    POSITIVE LOGITS
    很
    0.38
     smells
    0.37
    Ro
    0.37
     Apr
    0.37
    Vir
    0.36
     Hulu
    0.36
    Strong
    0.36
    蟑
    0.36
     parec
    0.35
     sor
    0.35
    Activations Density 0.000%

    No Known Activations