© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119156
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_27_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
     succes
    0.41
     ensuring
    0.40
     Successful
    0.39
     wat
    0.38
     Succ
    0.38
    )->
    0.38
     working
    0.37
     throughout
    0.37
     phased
    0.37
     Leeds
    0.37
    POSITIVE LOGITS
    ційних
    0.41
    ϝ
    0.40
    abortion
    0.38
    idez
    0.37
    ISK
    0.37
    𒊬
    0.37
    ITARY
    0.37
    ža
    0.37
    內的
    0.36
    žem
    0.36
    Activations Density 0.000%

    No Known Activations