© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83937
    Prev
    Next
    INDEX
    Explanations

    Kro and key-value pairs

    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_0_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
    ian
    1.55
    ьте
    1.49
    ä
    1.29
    als
    1.28
    ien
    1.27
    ates
    1.19
     तरह
    1.19
    ary
    1.18
    них
    1.17
    ute
    1.16
    POSITIVE LOGITS
    ש
    1.95
    ла
    1.90
    ي
    1.84
    ش
    1.82
    ו
    1.71
    י
    1.67
    ना
    1.63
    ز
    1.59
    দ
    1.59
    ta
    1.55
    Activations Density 0.000%

    No Known Activations