© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48508
    Prev
    Next
    INDEX
    Explanations

    .

    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_55_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
    ′,
    0.46
     वीं
    0.41
    itabbo
    0.41
    ″]
    0.39
     ರಿಂದ
    0.38
    ème
    0.37
    οι
    0.37
    ″
    0.37
    ′
    0.36
    8
    0.35
    POSITIVE LOGITS
     serenity
    0.44
     nearly
    0.42
     tranquility
    0.40
     synes
    0.39
     ant
    0.38
     Magna
    0.38
     bele
    0.37
     unimaginable
    0.37
     Type
    0.36
     almost
    0.36
    Activations Density 0.002%

    No Known Activations