© 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. 203199
    Prev
    Next
    INDEX
    Explanations

    linking to web resources

    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
    arged
    0.47
     طراحی
    0.40
    starcore
    0.40
    Ꮘ
    0.39
     çağ
    0.39
    avorable
    0.39
     Хоро
    0.38
    ocally
    0.37
     Она
    0.37
     الشركة
    0.36
    POSITIVE LOGITS
    radar
    0.41
     radar
    0.39
    Telemetry
    0.36
    Encrypt
    0.35
    DOS
    0.35
    Radar
    0.35
     प्रतिद्व
    0.35
     lump
    0.34
    痕
    0.34
     telemetry
    0.34
    Activations Density 0.000%

    No Known Activations