© 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. 162433
    Prev
    Next
    INDEX
    Explanations

    ALDI, Ahnen, Alba, Alte

    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
    '
    1.61
    ي
    1.24
    י
    1.21
    at
    1.10
    م
    1.06
    ని
    1.02
    ‘
    1.00
    '[
    0.99
    \
    0.95
    with
    0.95
    POSITIVE LOGITS
    h
    1.23
    </tr>
    0.96
    タンク
    0.93
    in
    0.90
    å
    0.90
    кими
    0.88
    ↵
    0.83
     swatch
    0.79
    ной
    0.79
    p
    0.79
    Activations Density 0.000%

    No Known Activations