© 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. 168170
    Prev
    Next
    INDEX
    Explanations

    say main

    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
    ᄃ
    0.44
    лично
    0.42
    (*)
    0.40
    (~
    0.39
    📁
    0.39
     પ્રય
    0.38
     striving
    0.37
    禳
    0.37
     Carole
    0.36
    وض
    0.36
    POSITIVE LOGITS
    #
    0.49
     obtención
    0.48
     obtain
    0.46
     getCurrent
    0.45
     Obtaining
    0.44
     None
    0.44
     False
    0.44
     uzys
    0.43
     obtains
    0.41
     pass
    0.41
    Activations Density 0.001%

    No Known Activations