© 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. 82978
    Prev
    Next
    INDEX
    Explanations

    transformers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    constraintlayout
    0.39
    tenths
    0.36
    śc
    0.35
    Mos
    0.35
    ArrayList
    0.34
    Cabinet
    0.33
    wav
    0.33
    ㄴ
    0.33
     dvs
    0.32
    Ave
    0.32
    POSITIVE LOGITS
    ეტ
    0.32
     gimm
    0.32
     रीजन
    0.32
     telescopes
    0.32
     হেতু
    0.32
    }^{*}$
    0.32
     geometries
    0.31
    स्ट्री
    0.31
    фта
    0.30
     Eno
    0.30
    Activations Density 0.004%

    No Known Activations