© 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. 157981
    Prev
    Next
    INDEX
    Explanations

    nirvana, iridophores, banana

    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
    it
    1.52
    ä
    1.52
     are
    1.48
    ي
    1.22
    ী
    1.20
     it
    1.13
    are
    1.12
     or
    1.09
    A
    1.09
    ת
    1.09
    POSITIVE LOGITS
    くちゃ
    0.85
    ことを
    0.84
    ように
    0.83
     раствор
    0.80
     plaisir
    0.79
    direccion
    0.79
     веке
    0.79
     πρώτη
    0.78
     mắn
    0.77
     нулю
    0.77
    Activations Density 0.000%

    No Known Activations