© 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. 156052
    Prev
    Next
    INDEX
    Explanations

    Van

    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
    eli
    0.41
    აშ
    0.39
     buzz
    0.38
    vient
    0.38
    assets
    0.38
     tenets
    0.38
     CORE
    0.38
    ි
    0.38
    াশ
    0.38
    Ȧ
    0.38
    POSITIVE LOGITS
     INVALID
    0.41
    Invalid
    0.40
    Vin
    0.40
    жны
    0.40
    Drive
    0.38
    كت
    0.38
    북
    0.37
    中国
    0.37
    Ꮏ
    0.37
     luc
    0.36
    Activations Density 0.000%

    No Known Activations