© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10628
    Prev
    Next
    INDEX
    Explanations

    r_squared

    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_40_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
    estima
    0.38
    Opacity
    0.36
    浸
    0.36
    承認
    0.36
     بز
    0.36
     سنی
    0.35
    僖
    0.35
     cies
    0.34
     zadovol
    0.34
    軺
    0.33
    POSITIVE LOGITS
     R
    1.31
    R
    0.98
     Р
    0.80
     الر
    0.80
     आर
    0.79
    Ｒ
    0.72
    𝑅
    0.71
     הר
    0.70
    Р
    0.63
     r
    0.62
    Activations Density 0.020%

    No Known Activations