© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78104
    Prev
    Next
    INDEX
    Explanations

    punishment or penalty

    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_31_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
     Aralık
    0.36
    밋
    0.36
     건강
    0.36
    .>
    0.36
     Oat
    0.34
    rello
    0.34
     manually
    0.34
     Melissa
    0.34
     Clinic
    0.33
     Coord
    0.33
    POSITIVE LOGITS
     punitive
    0.47
    懲
    0.45
    罰
    0.43
     punishment
    0.42
     Punishment
    0.42
     penalties
    0.41
    罚
    0.41
    惩
    0.40
    譴
    0.39
     пошу
    0.39
    Activations Density 0.096%

    No Known Activations