© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206445
    Prev
    Next
    INDEX
    Explanations

    injection attacks

    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_10_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
    ↵↵
    0.36
     ataque
    0.36
     Attacks
    0.33
     Attack
    0.33
     \\
    0.32
    n
    0.31
     attack
    0.30
     attacking
    0.30
     attaque
    0.30
     attaqu
    0.30
    POSITIVE LOGITS
    L
    0.36
    T
    0.36
    ST
    0.34
    Sanchez
    0.34
    Electricity
    0.34
    Sold
    0.34
    SCO
    0.33
    Shel
    0.33
    SAR
    0.33
    TEX
    0.33
    Activations Density 0.008%

    No Known Activations