© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62449
    Prev
    Next
    INDEX
    Explanations

    Facebook and Instagram

    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_59_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
    <start_of_image>
    0.48
     Helmet
    0.45
    Helmet
    0.44
    Lets
    0.41
     quoted
    0.40
     Account
    0.40
     Construct
    0.40
     Suggest
    0.40
     written
    0.39
     Allows
    0.39
    POSITIVE LOGITS
    סים
    0.37
    股份
    0.37
     ದೂರ
    0.37
     वय
    0.36
    終
    0.36
     アメリカ
    0.35
    ellow
    0.35
     التش
    0.35
    প্রিল
    0.35
    สต์
    0.35
    Activations Density 0.001%

    No Known Activations