© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120641
    Prev
    Next
    INDEX
    Explanations

    dataset URLs

    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_27_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
    ለሁ
    0.39
    ਕਾਰ
    0.39
    Cheat
    0.38
    बुक
    0.37
     एप्पल
    0.37
    روی
    0.37
    ონ
    0.35
     僕
    0.35
    上涨
    0.34
    츈
    0.34
    POSITIVE LOGITS
     database
    0.38
     explicar
    0.38
     disag
    0.37
     User
    0.36
     Breeding
    0.35
     user
    0.35
     dataset
    0.35
     trauma
    0.35
     motivos
    0.35
     motorized
    0.35
    Activations Density 0.004%

    No Known Activations