© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50471
    Prev
    Next
    INDEX
    Explanations

    say '0' or 'o'

    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_55_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
    o
    1.08
    O
    1.00
    ο
    0.98
    و
    0.97
    ो
    0.96
    ō
    0.93
    о
    0.92
    Ο
    0.91
    ｏ
    0.90
    ো
    0.90
    POSITIVE LOGITS
    ুলের
    0.36
     addObject
    0.33
    नात
    0.32
     fronte
    0.32
     EntityManager
    0.31
    ಂಗ
    0.31
     operator
    0.31
    حظ
    0.31
     setObject
    0.31
     nouve
    0.31
    Activations Density 0.054%

    No Known Activations