© 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. 30788
    Prev
    Next
    INDEX
    Explanations

    Hugging Face or hate speech

    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
    බන්ධ
    0.43
    ﺹ
    0.36
     సంబంధ
    0.34
    encias
    0.34
    endim
    0.34
     destek
    0.34
     متحد
    0.34
     Abril
    0.33
    셜
    0.33
    랙
    0.33
    POSITIVE LOGITS
     ML
    0.34
    හු
    0.33
    啥
    0.33
    blockquote
    0.32
     Lif
    0.32
    ob
    0.32
    Bloc
    0.32
     누
    0.32
    作业
    0.32
    Wil
    0.32
    Activations Density 0.008%

    No Known Activations