© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253990
    Prev
    Next
    INDEX
    Explanations

    add

    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_56_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
     dial
    0.39
    श
    0.38
     institute
    0.38
    celle
    0.38
    institute
    0.37
     mandatory
    0.36
    baum
    0.36
    ayah
    0.35
    fer
    0.35
    orget
    0.34
    POSITIVE LOGITS
    加
    2.47
     加
    1.84
     dod
    1.30
     Dod
    1.20
     Add
    1.18
    Dod
    1.18
    を加
    1.16
    Add
    1.15
     add
    1.14
    add
    1.10
    Activations Density 0.003%

    No Known Activations