© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2029
    Prev
    Next
    INDEX
    Explanations

    thank you for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     DIO
    0.40
    能力
    0.40
    审批
    0.39
    ্টিফি
    0.39
    城堡
    0.39
    ّد
    0.38
     lengthening
    0.38
    ඪ
    0.36
    人生
    0.36
     விருது
    0.36
    POSITIVE LOGITS
    RegistrationBean
    0.40
    inness
    0.39
     very
    0.38
     earnest
    0.38
    uenti
    0.38
    ా
    0.38
     rất
    0.37
     sincerely
    0.37
     thay
    0.37
    iume
    0.36
    Activations Density 0.013%

    No Known Activations