© 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. 90596
    Prev
    Next
    INDEX
    Explanations

    Mountain View

    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
    т
    1.17
    ت
    0.97
    є
    0.79
     Lorsque
    0.73
    त
    0.72
     encontr
    0.70
    تهم
    0.70
    μα
    0.67
     comenc
    0.66
    ת
    0.65
    POSITIVE LOGITS
     to
    0.73
    ANT
    0.73
    AT
    0.71
    SI
    0.67
    ops
    0.65
    ENT
    0.64
    imonials
    0.63
    ITCH
    0.61
    IT
    0.59
    ounds
    0.59
    Activations Density 0.000%

    No Known Activations