© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132208
    Prev
    Next
    INDEX
    Explanations

    Subaru car models

    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_6_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
    从而
    0.99
    然后
    0.93
    ас
    0.93
    る
    0.86
    abhuto
    0.84
    <0x80>
    0.81
    <0x88>
    0.80
    ayutt
    0.79
    ları
    0.79
    ৫
    0.79
    POSITIVE LOGITS
    MA
    1.18
    ANG
    1.15
    AI
    1.07
    AIS
    1.06
    im
    1.05
    MS
    1.05
    OS
    1.04
    MI
    1.03
    TE
    1.02
    GA
    1.02
    Activations Density 0.000%

    No Known Activations