© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59879
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    د
    2.02
    ه
    1.70
    ח
    1.49
    其他
    1.38
    д
    1.26
    ز
    1.25
    ש
    1.09
    ش
    1.05
    h
    1.03
     in
    0.98
    POSITIVE LOGITS
    ೩
    0.85
    ﻟ
    0.80
    ್ಟ
    0.80
    と
    0.79
    {
    0.79
    ov
    0.78
    廝
    0.77
    лом
    0.77
    DA
    0.76
    oji
    0.76
    Activations Density 0.000%

    No Known Activations