© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5011
    Prev
    Next
    INDEX
    Explanations

    describing the context or purpose

    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_40_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
    టో
    0.09
    vat
    0.08
    诸多
    0.08
    dimensions
    0.08
     many
    0.08
     OUR
    0.08
    咱
    0.08
     많은
    0.08
    ऍ
    0.07
     mnoh
    0.07
    POSITIVE LOGITS
     quienes
    0.09
    itabbo
    0.08
     overcast
    0.08
    工房
    0.08
    ibatkan
    0.08
     جنہوں
    0.08
     who
    0.08
    十五章
    0.08
    ogados
    0.08
    錒
    0.08
    Activations Density 1.477%

    No Known Activations