© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40504
    Prev
    Next
    INDEX
    Explanations

    Norwegian articles

    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_57_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
     вико
    0.54
     hon
    0.48
     bru
    0.40
     alle
    0.39
     ดิ
    0.39
    ᑉ
    0.39
     ALLE
    0.38
    Hon
    0.38
     disse
    0.36
     أ
    0.36
    POSITIVE LOGITS
     Eth
    0.59
     eth
    0.53
    Eth
    0.52
     ét
    0.51
     ens
    0.47
     ett
    0.45
    vil
    0.43
     envelope
    0.42
    వల
    0.42
    Et
    0.40
    Activations Density 0.000%

    No Known Activations