© 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. 45437
    Prev
    Next
    INDEX
    Explanations

    aden, adon, an, and ness suffixes

    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
    ৯
    0.82
    ן
    0.82
    ח
    0.80
    ৮
    0.79
    на
    0.77
    ير
    0.77
    ي
    0.77
    iş
    0.74
    твори
    0.73
    ৪
    0.73
    POSITIVE LOGITS
    il
    0.77
    és
    0.72
    اری
    0.70
    ad
    0.64
    ach
    0.62
    ag
    0.61
    ified
    0.59
    ouilles
    0.59
    おか
    0.58
    uka
    0.57
    Activations Density 0.001%

    No Known Activations