© 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. 197070
    Prev
    Next
    INDEX
    Explanations

    GitHub

    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
    主持
    0.38
    uml
    0.37
    狧
    0.37
    LAY
    0.36
    poetrycommunity
    0.36
    ണ
    0.36
    ర్య
    0.36
    ल्शियम
    0.36
    ⵄ
    0.35
    탭
    0.35
    POSITIVE LOGITS
     profile
    0.40
     magnitude
    0.38
     profil
    0.38
     profilo
    0.38
    coded
    0.37
    etele
    0.37
    ridor
    0.37
     stranger
    0.36
     magazine
    0.35
    profile
    0.35
    Activations Density 0.001%

    No Known Activations