© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122757
    Prev
    Next
    INDEX
    Explanations

    betrayal

    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_3_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
    ى
    0.84
    л
    0.78
    z
    0.76
     as
    0.73
    f
    0.66
    دي
    0.66
     此
    0.66
    琙
    0.64
    $),
    0.61
    v
    0.59
    POSITIVE LOGITS
    (
    0.86
    که
    0.81
     asesin
    0.79
    ల
    0.76
    ৫
    0.74
    ного
    0.74
    /
    0.74
    te
    0.72
    ﺍ
    0.69
     hypothes
    0.68
    Activations Density 0.000%

    No Known Activations