© 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. 34818
    Prev
    Next
    INDEX
    Explanations

    Doja Cat

    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
     uye
    0.71
     temprana
    0.68
     unha
    0.67
     Ú
    0.65
     slučaj
    0.65
    基づ
    0.64
     пря
    0.63
     በእ
    0.63
    垡
    0.63
     नया
    0.63
    POSITIVE LOGITS
    。\
    0.93
     are
    0.88
     as
    0.84
    air
    0.80
    dan
    0.80
    هایی
    0.77
    imme
    0.74
    𝐝
    0.73
     of
    0.72
    o
    0.72
    Activations Density 0.000%

    No Known Activations