© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215065
    Prev
    Next
    INDEX
    Explanations

    say "n"

    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_50_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
     fours
    0.38
     """",
    0.38
     ramo
    0.38
    Four
    0.37
    ūsų
    0.37
     гран
    0.37
    ҙ
    0.36
    classmethod
    0.36
     ग्रैंड
    0.36
    یە
    0.35
    POSITIVE LOGITS
    არ
    0.39
    wie
    0.36
    別
    0.35
     Rab
    0.34
    ይ
    0.33
    enschappen
    0.33
    研
    0.33
    пу
    0.33
    elez
    0.32
    뇨
    0.32
    Activations Density 0.002%

    No Known Activations