© 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. 111605
    Prev
    Next
    INDEX
    Explanations

    ag grid, agri-tourism, agri-renewal, agri-value, ag-ux, inhibition

    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
    '
    1.20
     It
    1.17
    ።
    1.17
    ských
    1.14
    )
    1.14
    。
    1.13
    s
    1.09
    1
    1.07
     at
    1.05
     Fernseh
    1.05
    POSITIVE LOGITS
    на
    1.22
    ות
    1.21
    ル
    1.20
    ak
    1.19
    i
    1.13
    ای
    1.08
    liness
    1.08
    و
    1.05
    ق
    1.05
    ק
    1.04
    Activations Density 0.001%

    No Known Activations