© 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. 127500
    Prev
    Next
    INDEX
    Explanations

    Konstanz, Constance

    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
    ience
    0.70
     hairpin
    0.68
    д
    0.67
    ier
    0.66
     recognition
    0.64
    K
    0.64
    ਇ
    0.64
    ↵
    0.63
     beginnings
    0.61
    N
    0.61
    POSITIVE LOGITS
    ।
    0.97
     الصوت
    0.87
    。
    0.87
    s
    0.86
    0
    0.86
    رک
    0.84
    ের
    0.83
     sukces
    0.82
    2
    0.82
    ों
    0.81
    Activations Density 0.000%

    No Known Activations