© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162539
    Prev
    Next
    INDEX
    Explanations

    ruin or fraud prevention

    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    л
    1.02
    い
    1.00
    ל
    0.91
     at
    0.84
    ل
    0.79
    ות
    0.78
    ]
    0.75
    ב
    0.75
     reorgan
    0.73
    いろいろ
    0.71
    POSITIVE LOGITS
    ai
    1.06
    2
    1.01
    га
    0.97
    erv
    0.89
    ا
    0.89
    ajú
    0.86
    اه
    0.86
    ные
    0.85
    اء
    0.85
    enen
    0.85
    Activations Density 0.000%

    No Known Activations