© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4388
    Prev
    Next
    INDEX
    Explanations

    harmful, normalize, contribute

    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
     środ
    0.42
     فیصلے
    0.38
     vü
    0.37
     Geist
    0.35
     licha
    0.35
     judiciaire
    0.35
     तु
    0.34
     \;
    0.34
    েন্টের
    0.34
    寸
    0.34
    POSITIVE LOGITS
     harm
    1.24
     Harm
    1.10
     harms
    1.07
    harm
    1.04
     harmed
    1.01
    Harm
    0.97
     harmful
    0.94
    harmed
    0.94
     damage
    0.86
    damage
    0.81
    Activations Density 0.459%

    No Known Activations