© 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. 10369
    Prev
    Next
    INDEX
    Explanations

    harmful content

    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
     SMC
    0.39
    PROVIDED
    0.39
     ဝ
    0.36
    ավ
    0.35
    ِينَ
    0.35
    方は
    0.34
    亭
    0.34
     [&](
    0.34
    endish
    0.34
     വാക്ക
    0.34
    POSITIVE LOGITS
     harm
    0.67
    harm
    0.55
     Harm
    0.54
     harms
    0.49
    Harm
    0.47
     injury
    0.46
    harmonic
    0.43
     Injury
    0.42
     harmed
    0.41
    harmed
    0.41
    Activations Density 0.054%

    No Known Activations