© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56535
    Prev
    Next
    INDEX
    Explanations

    malicious 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_11_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
     NC
    0.21
     Kinn
    0.19
     tegas
    0.19
     टु
    0.19
    larına
    0.19
     AR
    0.19
    ू
    0.19
    ?</
    0.19
     DF
    0.18
     potencial
    0.18
    POSITIVE LOGITS
    σει
    0.28
    вает
    0.24
    σε
    0.24
    сси
    0.24
    humidité
    0.23
    καν
    0.23
    ções
    0.22
    undi
    0.22
    ек
    0.22
    waf
    0.21
    Activations Density 0.006%

    No Known Activations