© 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. 113174
    Prev
    Next
    INDEX
    Explanations

    leaching

    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
    Not in Any Lists

    No Comments

    Negative Logits
    to
    1.69
    1.60
    ור
    1.48
    า
    1.45
     be
    1.41
    та
    1.30
    ва
    1.23
    મ
    1.21
    й
    1.13
    लभ
    1.11
    POSITIVE LOGITS
    ”
    1.13
    تين
    1.13
    ۰
    1.11
    টি
    1.03
    لت
    1.02
    ní
    1.00
    ми
    0.96
    います
    0.95
    }
    0.95
    리의
    0.93
    Activations Density 0.000%

    No Known Activations