© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205865
    Prev
    Next
    INDEX
    Explanations

    self-defense Article 51

    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_37_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
     hust
    0.40
     Đình
    0.39
    назна
    0.37
     amn
    0.37
    0.37
     Hust
    0.35
     plazas
    0.35
    铜
    0.35
     risc
    0.35
     elevations
    0.34
    POSITIVE LOGITS
     willpower
    0.71
    Strength
    0.54
    Self
    0.53
     Kontrolle
    0.52
     Self
    0.49
    Unlimited
    0.49
    Control
    0.49
     Strength
    0.49
     self
    0.48
     सेल्फ
    0.48
    Activations Density 0.003%

    No Known Activations