© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213726
    Prev
    Next
    INDEX
    Explanations

    flaw

    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_50_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
    incu
    0.40
    ठे
    0.38
    ரிக்க
    0.37
    㶪
    0.36
     ದು
    0.36
     তদ
    0.35
    త్తు
    0.35
     Glyph
    0.35
    鈷
    0.35
    胝
    0.35
    POSITIVE LOGITS
     Fl
    2.58
    Fl
    2.45
    fl
    2.39
     fl
    1.96
     Flock
    1.53
     FL
    1.48
     फ्ल
    1.48
    FL
    1.47
     ফ্ল
    1.45
     flute
    1.43
    Activations Density 0.001%

    No Known Activations