© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246043
    Prev
    Next
    INDEX
    Explanations

    sorting and removing duplicates

    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
     circonstances
    0.40
    トレンド
    0.39
    音
    0.38
    subset
    0.36
     موض
    0.35
    sb
    0.35
    erp
    0.34
    千
    0.34
     sb
    0.34
    increase
    0.34
    POSITIVE LOGITS
     സർ
    0.41
     vantage
    0.38
     Hua
    0.37
     vend
    0.37
    គួរ
    0.37
     com
    0.37
     paddling
    0.37
     IMS
    0.36
     [--
    0.36
    DJANGO
    0.36
    Activations Density 0.000%

    No Known Activations