© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167814
    Prev
    Next
    INDEX
    Explanations

    Fl

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     फ़
    0.68
     फ़
    0.68
    ಫ
    0.65
     fi
    0.63
     ஃப
    0.63
    Ф
    0.61
     ಫ
    0.58
     Ф
    0.57
    ஃப
    0.57
    ఫ
    0.57
    POSITIVE LOGITS
    Fl
    1.97
     fl
    1.95
     Fl
    1.95
    fl
    1.91
     FL
    1.70
    Flam
    1.70
    FL
    1.61
     FLA
    1.60
     فل
    1.59
     फ्ल
    1.56
    Activations Density 0.003%

    No Known Activations