© 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. 34567
    Prev
    Next
    INDEX
    Explanations

    คำ

    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
     ire
    0.37
     suspect
    0.37
     BA
    0.36
     ve
    0.35
    inity
    0.35
     Piano
    0.35
    ḫ
    0.35
    nere
    0.35
     мать
    0.35
    WAY
    0.34
    POSITIVE LOGITS
    ത്തന
    0.43
     Zeeman
    0.41
    ʇ
    0.39
     আকা
    0.39
    łop
    0.38
    íoch
    0.37
    Includes
    0.37
     Dop
    0.37
    谢
    0.36
     Disorders
    0.36
    Activations Density 0.000%

    No Known Activations