© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62112
    Prev
    Next
    INDEX
    Explanations

    vantage point / bootstrap

    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_11_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
    2
    0.40
    >
    0.37
    Vietnam
    0.35
    João
    0.35
     chirop
    0.34
    Germany
    0.34
    Franz
    0.32
    Bots
    0.32
    기에
    0.32
    ituus
    0.31
    POSITIVE LOGITS
    al
    0.41
     prosecute
    0.41
     конкурс
    0.40
     শীর্ষক
    0.39
    ﾝ
    0.38
     সিনে
    0.37
    اك
    0.35
    يل
    0.35
     senador
    0.35
    ла
    0.35
    Activations Density 0.001%

    No Known Activations