© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21302
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    слан
    0.41
    vestre
    0.41
    মার
    0.40
     धा
    0.40
    سل
    0.39
    pan
    0.39
    豆
    0.39
    琴
    0.38
    amol
    0.37
    ctuaries
    0.37
    POSITIVE LOGITS
    アクション
    0.40
     ಅನ
    0.39
     Coch
    0.38
     Francia
    0.37
     pretty
    0.37
    critic
    0.37
     pund
    0.37
     Eds
    0.36
     anesthetic
    0.36
     FRANCE
    0.36
    Activations Density 0.034%

    No Known Activations