© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197540
    Prev
    Next
    INDEX
    Explanations

    Crete

    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_15_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
     গাড়ি
    0.54
    c
    0.53
    örk
    0.51
    Peach
    0.47
     operar
    0.47
    ナル
    0.47
     traveller
    0.46
    Payroll
    0.46
    ionalmente
    0.46
     drivers
    0.46
    POSITIVE LOGITS
     Rupees
    0.56
    ⚭
    0.54
    )*
    0.54
    0.52
     занятия
    0.52
    坚
    0.52
    㒵
    0.52
    )。
    0.51
    ☆☆
    0.51
    }^
    0.50
    Activations Density 0.001%

    No Known Activations