© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158477
    Prev
    Next
    INDEX
    Explanations

    Fast Fourier Transform (FFT)

    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
    d
    1.37
    ला
    1.35
    c
    1.34
    на
    1.25
    ara
    1.20
    อยาก
    1.17
     are
    1.15
    aj
    1.12
    for
    1.10
    ро
    1.07
    POSITIVE LOGITS
    م
    1.23
    ول
    1.09
    ம்
    1.07
    보
    1.02
    ం
    0.99
     to
    0.97
    은
    0.96
    是
    0.95
     In
    0.93
    м
    0.93
    Activations Density 0.000%

    No Known Activations