© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29504
    Prev
    Next
    INDEX
    Explanations

    keyword, brand awareness, green zone, doi, fixed rate, moving average, suggested hashtags, keyboard navigation

    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_40_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
    싸
    0.45
    ഷ്യ
    0.41
    forbidden
    0.40
    Hack
    0.39
    शाही
    0.38
    ಲು
    0.38
    <unused28>
    0.38
    깍
    0.38
    ừa
    0.37
    逡
    0.37
    POSITIVE LOGITS
     SP
    0.41
    鍝
    0.39
     naturel
    0.39
     MOV
    0.37
     SEN
    0.36
     CC
    0.36
     SPL
    0.36
    BASELINE
    0.36
    ैर्य
    0.36
     SHOW
    0.35
    Activations Density 0.040%

    No Known Activations