© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1450
    Prev
    Next
    INDEX
    Explanations

    kh

    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_39_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
    傚
    0.36
     पहाड़
    0.36
    كاته
    0.35
    aped
    0.34
    igent
    0.34
     monsters
    0.34
     $(`.
    0.34
    ίκη
    0.34
     वातावरण
    0.33
     सां
    0.33
    POSITIVE LOGITS
     kh
    0.50
     Kh
    0.50
    Kh
    0.47
    kh
    0.45
    KH
    0.45
    ẖ
    0.41
     ఖ
    0.40
     especialmente
    0.40
     الخ
    0.40
    血
    0.39
    Activations Density 0.019%

    No Known Activations