© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260105
    Prev
    Next
    INDEX
    Explanations

    code block endings

    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_22_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
    CEO
    0.39
    <unused82>
    0.38
     ceo
    0.38
    <unused83>
    0.38
     Fallon
    0.37
    綬
    0.37
    कहां
    0.37
    <unused2>
    0.36
    ^*\
    0.36
    滑
    0.36
    POSITIVE LOGITS
     outbursts
    0.47
     violently
    0.47
     የማ
    0.42
    readLine
    0.41
     prophecy
    0.41
     reentry
    0.40
     spe
    0.40
     vocal
    0.39
     фра
    0.39
     subjug
    0.39
    Activations Density 0.000%

    No Known Activations