© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137926
    Prev
    Next
    INDEX
    Explanations

    timeframe indicators

    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_12_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
     sebagaimana
    0.50
     Shaf
    0.50
    𝓑
    0.49
    ARMA
    0.48
    ర్
    0.48
    দ্র
    0.48
     जैसा
    0.47
     发表
    0.47
     Akar
    0.46
    ARGB
    0.46
    POSITIVE LOGITS
    chée
    0.55
     το
    0.54
     νε
    0.54
     $\
    0.53
     municipality
    0.52
     council
    0.51
     translation
    0.51
    ною
    0.51
     deregulation
    0.50
     mairie
    0.50
    Activations Density 0.001%

    No Known Activations