© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226517
    Prev
    Next
    INDEX
    Explanations

    specific edition

    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_10_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
     чисел
    0.49
    बाइक
    0.49
    uctive
    0.48
    wiek
    0.47
    కరించ
    0.46
    sparsebundle
    0.46
    ಧಾರವಾಡ
    0.45
    걱
    0.45
    𝕂
    0.45
    換え
    0.45
    POSITIVE LOGITS
     Pem
    0.52
     pore
    0.50
     for
    0.49
     (
    0.47
    ]
    0.46
     genre
    0.46
     search
    0.46
     Pore
    0.45
    for
    0.45
    ii
    0.45
    Activations Density 0.000%

    No Known Activations