© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200814
    Prev
    Next
    INDEX
    Explanations

    alimento**

    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_6_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
    it
    1.38
    ä
    1.27
    ot
    1.23
    ut
    1.11
    ine
    1.03
    is
    1.02
    itie
    0.98
    ra
    0.97
    pt
    0.97
    ре
    0.97
    POSITIVE LOGITS
     as
    1.22
     la
    1.09
    וף
    1.03
    Д
    1.00
     ב
    0.98
    。”
    0.97
    ്ലാ
    0.96
    וש
    0.95
     by
    0.95
     of
    0.94
    Activations Density 0.000%

    No Known Activations