© 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. 21438
    Prev
    Next
    INDEX
    Explanations

    x

    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
    ။
    0.41
    e
    0.41
    ॥
    0.41
    !!
    0.39
    side
    0.38
    الس
    0.37
    )$
    0.37
    ‘
    0.37
    στο
    0.37
    मैन
    0.36
    POSITIVE LOGITS
     anything
    0.63
     everything
    0.61
     something
    0.60
     etwas
    0.54
    Something
    0.51
     Something
    0.50
     whatever
    0.50
     qualcosa
    0.50
     wszystko
    0.49
     someone
    0.46
    Activations Density 0.006%

    No Known Activations