© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175808
    Prev
    Next
    INDEX
    Explanations

    paperwork

    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_20_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
     mystery
    0.50
    mystery
    0.48
     Vat
    0.46
     amigo
    0.45
    setVerticalGroup
    0.45
    メモ
    0.43
     Bajaj
    0.43
     प
    0.43
     TIME
    0.43
     prone
    0.43
    POSITIVE LOGITS
     biofilms
    0.47
    ouilles
    0.44
    غذ
    0.43
    חים
    0.42
     সিলে
    0.41
     compatibles
    0.41
     있는지
    0.40
     وہاں
    0.40
    涎
    0.39
    ندی
    0.39
    Activations Density 0.001%

    No Known Activations