© 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. 156882
    Prev
    Next
    INDEX
    Explanations

    ds commands and patterns

    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
    いますが
    1.34
    ра
    1.26
    д
    1.26
    いき
    1.23
    いた
    1.15
    ።
    1.13
    のである
    1.12
     nešto
    1.09
    し
    1.06
    ように
    1.05
    POSITIVE LOGITS
     for
    1.70
    el
    1.51
     by
    1.39
    for
    1.34
     I
    1.27
    us
    1.23
    ad
    1.23
    0
    1.16
    is
    1.15
     (
    1.15
    Activations Density 0.002%

    No Known Activations