© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106060
    Prev
    Next
    INDEX
    Explanations

    debunking

    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_1_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
    i
    1.78
    ↵
    1.38
    و
    1.31
    ي
    1.14
    y
    1.12
    ни
    1.10
    י
    1.09
    the
    1.05
    ना
    1.02
    नो
    1.02
    POSITIVE LOGITS
     are
    1.52
     is
    1.19
    ৪
    1.16
     be
    1.12
    ية
    1.10
     as
    1.07
    ের
    1.05
    ري
    1.05
     in
    1.03
    ENT
    1.00
    Activations Density 0.000%

    No Known Activations