© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93122
    Prev
    Next
    INDEX
    Explanations

    privilege escalation

    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
    2
    0.53
    묭
    0.52
    đer
    0.50
    ड्यूल
    0.49
    <
    0.49
     longing
    0.48
    ]("
    0.47
    laf
    0.47
     effector
    0.46
    ၂
    0.46
    POSITIVE LOGITS
    ية
    0.63
    يًا
    0.52
     Laboratories
    0.52
     Analytical
    0.50
    ത്ത്
    0.50
    та
    0.50
    itty
    0.50
     кто
    0.49
    ياً
    0.49
     Strang
    0.49
    Activations Density 0.000%

    No Known Activations