© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131209
    Prev
    Next
    INDEX
    Explanations

    jailbreak

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    न्ड
    0.41
    ц
    0.38
    ribut
    0.35
    namespaces
    0.35
     diseased
    0.34
     sharpening
    0.34
    FieldIndex
    0.33
     Chowdh
    0.33
    팅
    0.33
     clustered
    0.33
    POSITIVE LOGITS
     yell
    0.52
     PEAR
    0.48
    Crystal
    0.48
     Crystal
    0.47
     ម
    0.45
     yells
    0.45
     objetivos
    0.45
     ウェ
    0.45
     crystal
    0.44
     yelling
    0.42
    Activations Density 0.001%

    No Known Activations