© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50158
    Prev
    Next
    INDEX
    Explanations

    percentages and ratios

    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_30_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
    counts
    0.38
    筅
    0.38
    延長
    0.38
    flat
    0.37
     fontweight
    0.37
    Housing
    0.36
     Housing
    0.36
    꾀
    0.36
    alanine
    0.35
    Homes
    0.35
    POSITIVE LOGITS
    %。
    0.53
    %；
    0.50
    %")
    0.49
     porcentaje
    0.48
    %!
    0.46
    %=
    0.45
    %),
    0.45
     प्रतिशत
    0.44
     процентов
    0.44
    %).
    0.44
    Activations Density 0.045%

    No Known Activations