© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260953
    Prev
    Next
    INDEX
    Explanations

    under UI

    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_5_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
    i
    2.11
    ي
    1.44
    x
    1.41
    3
    1.38
    it
    1.33
    ut
    1.30
    י
    1.29
    e
    1.25
    at
    1.21
    al
    1.21
    POSITIVE LOGITS
    speople
    1.27
     It
    1.16
    ち
    1.12
    ید
    1.10
    л
    1.10
    खास्त
    1.08
    inį
    1.07
    し
    1.07
    اری
    1.05
     도움
    1.05
    Activations Density 0.000%

    No Known Activations