© 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. 44297
    Prev
    Next
    INDEX
    Explanations

    Am or amorphous

    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
    =='
    0.72
    ؟.
    0.70
    ۔
    0.69
    ೊ
    0.68
    Мо
    0.67
    莯
    0.66
    ()).
    0.65
    ).\\
    0.64
    )،
    0.64
    ორცი
    0.63
    POSITIVE LOGITS
     a
    0.75
    ay
    0.71
    at
    0.67
    diamond
    0.67
    as
    0.64
    a
    0.62
    f
    0.62
    !
    0.62
    it
    0.60
    ↵
    0.60
    Activations Density 0.007%

    No Known Activations