© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209926
    Prev
    Next
    INDEX
    Explanations

    offensive cartoons and 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_20_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
     getContentPane
    0.44
    গম
    0.42
     fisk
    0.42
    π
    0.41
    izability
    0.41
     ανα
    0.41
    UnityEngine
    0.41
    np
    0.40
     gene
    0.40
     autant
    0.39
    POSITIVE LOGITS
     दुश्मन
    0.47
    盟
    0.43
    鷗
    0.40
     немец
    0.39
     lâ
    0.39
     Filosof
    0.39
     Scenic
    0.38
     tedes
    0.38
    फूल
    0.38
     német
    0.38
    Activations Density 0.000%

    No Known Activations