© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206525
    Prev
    Next
    INDEX
    Explanations

    meteors

    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_46_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
    偏
    0.45
     Opinions
    0.41
    XZ
    0.38
     xv
    0.38
    inträ
    0.37
     Aspects
    0.37
     નિર્ણ
    0.36
     precon
    0.35
    enciales
    0.35
    赫
    0.35
    POSITIVE LOGITS
    Meteor
    0.41
    ប់
    0.39
     Meteor
    0.39
    paw
    0.39
     meteor
    0.38
     પડી
    0.38
     जैसी
    0.37
     blowing
    0.36
     Vish
    0.36
     chilly
    0.36
    Activations Density 0.001%

    No Known Activations