© 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. 44254
    Prev
    Next
    INDEX
    Explanations

    beyond their

    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
     కీల
    0.29
    σουν
    0.25
    ค
    0.24
    ھیں
    0.24
    ეხ
    0.24
    支払
    0.24
    şu
    0.24
    وی
    0.24
     Associação
    0.24
    婧
    0.23
    POSITIVE LOGITS
     +\
    0.31
     cricket
    0.30
    drama
    0.29
     +
    0.29
    tourism
    0.28
     barbers
    0.28
    <0x0D>
    0.27
     February
    0.27
     highway
    0.27
     robbery
    0.27
    Activations Density 0.009%

    No Known Activations