© 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. 27227
    Prev
    Next
    INDEX
    Explanations

    prep time, cook time

    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
     जीएस
    0.38
    гам
    0.35
     Eleven
    0.35
    ｺ
    0.34
    anager
    0.34
     अंतराल
    0.34
    嫦
    0.34
    GRAM
    0.33
    amist
    0.33
    FRAME
    0.33
    POSITIVE LOGITS
     flying
    0.39
     авиа
    0.37
     Flying
    0.36
    地面
    0.34
    Flying
    0.34
     minimum
    0.34
     aviation
    0.34
    ẽ
    0.34
    越
    0.34
     بگیر
    0.33
    Activations Density 0.004%

    No Known Activations