© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123084
    Prev
    Next
    INDEX
    Explanations

    Uma Musume, mouse, pad

    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_3_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
    지
    1.12
    ных
    0.80
    <0x0D>
    0.76
    ങ്ങൾ
    0.76
     değerli
    0.75
    די
    0.73
    ف
    0.73
    지로
    0.72
    ের
    0.71
     Docsity
    0.69
    POSITIVE LOGITS
    ن
    0.84
    त
    0.61
    在那里
    0.61
    л
    0.61
    з
    0.61
    shaw
    0.61
    n
    0.60
    asse
    0.59
     توڑ
    0.59
    к
    0.59
    Activations Density 0.002%

    No Known Activations