© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83089
    Prev
    Next
    INDEX
    Explanations

    public

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    вий
    0.42
    Att
    0.41
    Suffix
    0.41
    ATP
    0.40
    NA
    0.39
    Attenuation
    0.37
    ojen
    0.37
    Ń
    0.37
    ÑA
    0.36
     N
    0.36
    POSITIVE LOGITS
    ற்க
    0.40
     Qxc
    0.39
    love
    0.38
     Gabriele
    0.38
     selam
    0.38
    팔
    0.38
    scene
    0.37
    alous
    0.37
     tasse
    0.36
     hudson
    0.36
    Activations Density 0.004%

    No Known Activations