© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148895
    Prev
    Next
    INDEX
    Explanations

    normal person

    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_23_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
     curso
    0.40
     студент
    0.40
    цин
    0.38
     quos
    0.38
    公共
    0.37
     làn
    0.37
    侎
    0.37
     acquis
    0.37
     લાગ
    0.37
    ผู้ตัดสิน
    0.36
    POSITIVE LOGITS
    涳
    0.38
    <h5>
    0.37
    偐
    0.36
    ?";
    0.35
     एप्लिकेशन
    0.35
    ுற
    0.34
    真實
    0.34
    작
    0.34
    ндай
    0.34
     Validator
    0.34
    Activations Density 0.000%

    No Known Activations