© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204758
    Prev
    Next
    INDEX
    Explanations

    table header

    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
    Dur
    0.42
    实行
    0.41
     trwa
    0.41
    Care
    0.40
    $^{
    0.40
    Representative
    0.38
    㺫
    0.38
    Pink
    0.38
    刽
    0.38
    Curve
    0.38
    POSITIVE LOGITS
    מ
    0.38
     creators
    0.38
     collaborate
    0.37
     वजह
    0.36
     삼성
    0.36
    രും
    0.35
     samsung
    0.35
    σκεται
    0.35
     fehlt
    0.35
     certainty
    0.34
    Activations Density 0.000%

    No Known Activations