© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178880
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation

    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
     आपने
    0.43
     Za
    0.39
     Arthur
    0.39
     Opportunities
    0.38
     Barley
    0.38
    ád
    0.38
     Z
    0.38
     Isaac
    0.38
     Hin
    0.38
     Johnny
    0.37
    POSITIVE LOGITS
     simonsen
    0.42
     nonexpansive
    0.39
     expts
    0.37
     hadrons
    0.37
    ሥ
    0.36
    ريع
    0.36
    মাত
    0.35
     diastolic
    0.35
     ignite
    0.35
     undersea
    0.35
    Activations Density 0.002%

    No Known Activations