© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43669
    Prev
    Next
    INDEX
    Explanations

    Polish words and endings

    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_3_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
    יר
    0.71
    య
    0.70
    イベント
    0.69
    ’
    0.69
    ون
    0.68
    پ
    0.68
    ς
    0.68
    ის
    0.68
    ید
    0.67
    ਤਾ
    0.67
    POSITIVE LOGITS
    }
    0.94
    n
    0.85
     I
    0.82
    ti
    0.82
    li
    0.80
    z
    0.78
    t
    0.75
    an
    0.73
    l
    0.72
    til
    0.71
    Activations Density 0.000%

    No Known Activations