© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226751
    Prev
    Next
    INDEX
    Explanations

    often overlooked

    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_6_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
    tgt
    0.77
    大
    0.76
     or
    0.75
    하다
    0.74
    ната
    0.74
     عند
    0.73
    s
    0.73
    tans
    0.73
    一大
    0.72
    tive
    0.72
    POSITIVE LOGITS
    \
    1.18
    ری
    1.05
     the
    1.02
    ق
    0.94
    ri
    0.92
    9
    0.92
     bandes
    0.88
    -
    0.84
    oh
    0.83
    You
    0.82
    Activations Density 0.001%

    No Known Activations