© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112557
    Prev
    Next
    INDEX
    Explanations

    Plus beaux villages

    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_2_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
    ,
    1.05
    ant
    0.81
    ension
    0.69
    :
    0.68
    ல்
    0.67
    ances
    0.64
    ्स
    0.63
    )
    0.62
     to
    0.57
    िन
    0.57
    POSITIVE LOGITS
    و
    0.97
    ه
    0.89
    ה
    0.87
    ت
    0.87
    ו
    0.85
    ка
    0.82
    т
    0.81
    H
    0.80
    י
    0.76
    P
    0.74
    Activations Density 0.002%

    No Known Activations