© 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. 34240
    Prev
    Next
    INDEX
    Explanations

    wrong

    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
    ⢸
    0.39
    𝐜
    0.36
     vasomotor
    0.36
    স্ফ
    0.36
    ോഷ
    0.35
    珈
    0.35
    潸
    0.35
    푐
    0.34
    כו
    0.34
    fov
    0.34
    POSITIVE LOGITS
     wr
    1.97
    Wr
    1.88
    wr
    1.85
     WR
    1.81
    WR
    1.78
     Wr
    1.77
     writ
    1.31
     вра
    1.31
     Wrangler
    1.28
     Wrang
    1.27
    Activations Density 0.007%

    No Known Activations