© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241972
    Prev
    Next
    INDEX
    Explanations

    solving for variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    禟
    0.42
     весе
    0.40
    త్ప
    0.39
     modelled
    0.39
     Grafton
    0.37
    htb
    0.37
    ठ
    0.36
    HST
    0.36
    --',
    0.35
     թ
    0.35
    POSITIVE LOGITS
    的に
    0.41
    plic
    0.41
     richness
    0.38
    确定
    0.37
    artet
    0.37
    رمان
    0.37
     anticipates
    0.37
     standpoint
    0.37
    Ꮿ
    0.36
     dichiar
    0.36
    Activations Density 0.001%

    No Known Activations