© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240563
    Prev
    Next
    INDEX
    Explanations

    role, system, user

    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_25_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
     protiv
    0.43
    ="{
    0.37
     jasper
    0.37
    =\{
    0.37
     করিতেছিল
    0.36
     Ehrlich
    0.36
    গল
    0.35
     Herb
    0.35
     mainstay
    0.35
     остальные
    0.35
    POSITIVE LOGITS
    Escolhido
    0.39
     αρκε
    0.38
     participación
    0.38
     porté
    0.37
    好
    0.37
     नॉलेज
    0.36
     especial
    0.35
     एजुकेशन
    0.35
     μεγ
    0.35
    غن
    0.35
    Activations Density 0.000%

    No Known Activations