© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179427
    Prev
    Next
    INDEX
    Explanations

    brands and models

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    pear
    0.42
     Dear
    0.42
    whale
    0.41
     Gazz
    0.40
     Goodwin
    0.39
    чин
    0.39
    faulse
    0.38
    羍
    0.38
    ర్చ
    0.38
     Dur
    0.37
    POSITIVE LOGITS
     Roo
    0.48
    榎
    0.44
     randomNumber
    0.43
    હેરા
    0.42
     synt
    0.41
     kemenangan
    0.41
     sekar
    0.39
     Schnee
    0.39
    रुख
    0.39
    博
    0.39
    Activations Density 0.004%

    No Known Activations