© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11576
    Prev
    Next
    INDEX
    Explanations

    property and construction

    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_13_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
    :
    0.12
    ?
    0.11
    idar
    0.10
    ion
    0.10
    atable
    0.10
     ότι
    0.10
    ваемых
    0.10
    on
    0.10
     عجیب
    0.10
     Index
    0.10
    POSITIVE LOGITS
    Workbench
    0.11
    સિંહ
    0.11
     panch
    0.10
    Segments
    0.10
     Panch
    0.10
    ｙ
    0.10
    ডি
    0.10
     Jharkhand
    0.10
     मुस्लिम
    0.10
     partialX
    0.10
    Activations Density 0.043%

    No Known Activations