© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5494
    Prev
    Next
    INDEX
    Explanations

    injection or shot

    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_38_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
     স্ট্যান্ড
    0.41
     optimisation
    0.38
    Hack
    0.37
     অতীতের
    0.37
    աք
    0.37
     بذ
    0.37
    Ꮖ
    0.36
     сра
    0.36
     recursion
    0.35
    خری
    0.35
    POSITIVE LOGITS
     injections
    1.46
     injection
    1.43
     injecting
    1.34
     injected
    1.32
    注射
    1.31
     inject
    1.30
     needle
    1.29
     Injection
    1.28
    injection
    1.27
    針
    1.27
    Activations Density 0.065%

    No Known Activations