© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32525
    Prev
    Next
    INDEX
    Explanations

    Joker, carries, mischievous

    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_31_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
    大小
    0.38
    Heaven
    0.38
    着
    0.36
    vae
    0.35
    天使
    0.35
     ലൈ
    0.35
    Angel
    0.34
    黑
    0.34
    Black
    0.33
    NIH
    0.33
    POSITIVE LOGITS
    𝐤
    0.39
    䄪
    0.38
     Paddle
    0.37
     Raspberry
    0.37
     بخوان
    0.37
     gad
    0.37
    logfile
    0.37
     nett
    0.36
     paddle
    0.35
     Idi
    0.35
    Activations Density 0.055%

    No Known Activations