© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30770
    Prev
    Next
    INDEX
    Explanations

    Thanks and Best closings

    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_40_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
     ❤️
    0.46
    愛
    0.45
     love
    0.43
    爱
    0.43
     LOVE
    0.42
     ❤
    0.41
     ♥
    0.41
     爱
    0.41
    حب
    0.40
     любов
    0.39
    POSITIVE LOGITS
    ഷണ
    0.42
    docs
    0.41
     Drive
    0.38
     Abst
    0.38
    Gard
    0.38
     docs
    0.38
    Docs
    0.37
    Shin
    0.37
     Folks
    0.37
     چاہیے
    0.37
    Activations Density 0.005%

    No Known Activations