© 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. 162485
    Prev
    Next
    INDEX
    Explanations

    ritira

    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
    EN
    0.98
    ání
    0.91
    ，
    0.89
    ς
    0.88
    2
    0.86
    И
    0.84
    Е
    0.82
    0
    0.80
    ओं
    0.79
    }$(
    0.79
    POSITIVE LOGITS
    ad
    1.68
     by
    1.45
     was
    1.32
    ת
    1.29
    า
    1.28
     كان
    1.27
    та
    1.27
    to
    1.26
    an
    1.25
     or
    1.23
    Activations Density 0.000%

    No Known Activations