© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13240
    Prev
    Next
    INDEX
    Explanations

    open-source, tools, libraries

    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
    ı
    0.27
    ui
    0.26
    圭
    0.26
    ્યુ
    0.25
    Celeron
    0.25
     madrugada
    0.25
     soie
    0.24
    ⅱ
    0.24
     самой
    0.24
    ую
    0.23
    POSITIVE LOGITS
    դ
    0.29
     Innov
    0.29
     Brought
    0.28
    ד
    0.28
     Inspire
    0.28
    诬
    0.27
     Learned
    0.27
     Committed
    0.26
    راتكم
    0.26
    azaar
    0.26
    Activations Density 0.206%

    No Known Activations