© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66604
    Prev
    Next
    INDEX
    Explanations

    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_41_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
     H
    1.84
     h
    1.45
    H
    1.45
     হ
    1.34
     ஹ
    1.34
     ह
    1.33
     హ
    1.22
     ჰ
    1.20
     હ
    1.19
     اله
    1.19
    POSITIVE LOGITS
     নারদ
    0.40
    矯
    0.39
     பணியாற்ற
    0.38
    diocese
    0.38
    つけた
    0.36
    ತರ
    0.36
    емой
    0.35
    ूटूथ
    0.35
    کروچ
    0.35
     ১৩২২
    0.34
    Activations Density 0.007%

    No Known Activations