© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84619
    Prev
    Next
    INDEX
    Explanations

    cidr, fished, elk

    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_0_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
    م
    1.47
     It
    1.39
    v
    1.37
    m
    1.36
    d
    1.32
    b
    1.31
    ii
    1.30
    al
    1.29
     In
    1.19
    man
    1.16
    POSITIVE LOGITS
    ↵
    1.27
    '
    1.20
    kách
    1.16
    কে
    1.16
    ５
    1.12
     blatantly
    1.11
    ᆺ
    1.11
    кле
    1.08
    কার
    1.07
     மாசுபாடு
    1.06
    Activations Density 0.000%

    No Known Activations