© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38171
    Prev
    Next
    INDEX
    Explanations

    many [plural noun]

    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
    2
    1.16
    3
    0.97
    can
    0.88
    1
    0.86
    ים
    0.83
    4
    0.83
    ς
    0.83
    ۲
    0.79
    е
    0.77
    c
    0.76
    POSITIVE LOGITS
    ن
    0.74
    婫
    0.73
    ong
    0.73
    
    0.72
    icca
    0.69
    کریاں
    0.69
    নমেন্ট
    0.68
    িক
    0.67
    री
    0.66
    า
    0.66
    Activations Density 0.003%

    No Known Activations