© 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. 113462
    Prev
    Next
    INDEX
    Explanations

    c followed by punctuation or options

    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
    д
    1.71
    د
    1.45
    주
    1.32
    大
    1.26
    지
    1.25
    ש
    1.25
    ために
    1.23
    ف
    1.23
    дят
    1.19
    어
    1.13
    POSITIVE LOGITS
    '
    1.18
    il
    1.16
    ک
    1.14
    ’
    1.09
    ва
    1.08
    s
    1.06
    <0xAE>
    1.05
    )
    0.98
    elin
    0.97
    <0xB9>
    0.96
    Activations Density 0.004%

    No Known Activations