© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79210
    Prev
    Next
    INDEX
    Explanations

    as you

    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_29_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
    있다
    0.36
    负
    0.36
     канал
    0.35
     Basel
    0.34
    قابل
    0.34
     Ster
    0.33
    аз
    0.33
    блема
    0.33
     russo
    0.32
     عمل
    0.32
    POSITIVE LOGITS
     হইয়৷
    0.40
     murderers
    0.38
     mediates
    0.37
    induction
    0.37
    numericUpDown
    0.37
    逹
    0.37
     detd
    0.37
    marginal
    0.36
    जनक
    0.36
     newApproved
    0.36
    Activations Density 0.002%

    No Known Activations