© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165005
    Prev
    Next
    INDEX
    Explanations

    ratings and stars

    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_31_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
    гина
    0.42
     சுண்ணா
    0.40
     వెంటనే
    0.38
    வுகளை
    0.38
    胍
    0.38
    使用的是
    0.37
    प्रमाणे
    0.37
     Bot
    0.36
    主办
    0.36
    太多
    0.35
    POSITIVE LOGITS
    ১০
    0.39
     ს
    0.38
    Harvard
    0.37
     welt
    0.36
    abilir
    0.35
     다섯
    0.35
     성
    0.35
     can
    0.34
     ½
    0.34
    ২১
    0.34
    Activations Density 0.000%

    No Known Activations