© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82196
    Prev
    Next
    INDEX
    Explanations

    control/interface terms

    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_53_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
    $-(
    0.43
    빅
    0.41
     み
    0.41
     رون
    0.39
    尉
    0.39
    雾
    0.38
    輝
    0.38
    .$-
    0.37
    ແມ
    0.37
     jon
    0.37
    POSITIVE LOGITS
    ControlButton
    0.52
     controla
    0.41
    CreateInfo
    0.40
     controllo
    0.39
    コントロール
    0.39
    Control
    0.39
    控制
    0.38
    Comma
    0.38
     Info
    0.38
    addLine
    0.38
    Activations Density 0.005%

    No Known Activations