© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205265
    Prev
    Next
    INDEX
    Explanations

    Zaleon attacks, Zale 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_6_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
    ed
    0.98
    i
    0.91
    vorm
    0.88
    એ
    0.85
    ის
    0.84
    teki
    0.79
    dır
    0.79
     Fransa
    0.78
     των
    0.76
    u
    0.76
    POSITIVE LOGITS
     at
    0.81
     é
    0.80
     arrhythmias
    0.77
     médicos
    0.77
    بن
    0.74
    њу
    0.72
    LING
    0.72
    ف
    0.70
    ारा
    0.68
    رم
    0.68
    Activations Density 0.000%

    No Known Activations