© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81908
    Prev
    Next
    INDEX
    Explanations

    according to data

    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_29_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
     పెరుగు
    0.41
     파일을
    0.40
    োদ
    0.38
     wrecked
    0.38
     เช่น
    0.37
    গরের
    0.37
    ಲ
    0.37
    यक
    0.36
    ະພັນ
    0.36
    संयुक्त
    0.36
    POSITIVE LOGITS
    Twig
    0.35
     exaggeration
    0.34
     guide
    0.34
    스템
    0.34
     uniquely
    0.33
     visualization
    0.33
    仅仅
    0.32
     meri
    0.32
    𝐯
    0.32
     exag
    0.32
    Activations Density 0.000%

    No Known Activations