© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51274
    Prev
    Next
    INDEX
    Explanations

    can

    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
     વૈ
    0.42
     Marlow
    0.39
    ورية
    0.36
     liber
    0.36
    条
    0.35
     株
    0.34
     ژ
    0.33
    hagen
    0.33
     rém
    0.33
     limitations
    0.33
    POSITIVE LOGITS
     violate
    0.46
     violates
    0.46
     violating
    0.46
     contaminated
    0.45
     unclean
    0.44
     violated
    0.44
     disobey
    0.43
    违
    0.43
     contradicts
    0.42
     Viola
    0.41
    Activations Density 0.079%

    No Known Activations