© 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. 161526
    Prev
    Next
    INDEX
    Explanations

    language fragments

    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
     It
    1.59
     to
    1.44
    in
    1.25
     In
    1.09
    ก
    1.07
    س
    1.05
    )。
    1.05
    ad
    0.99
     can
    0.99
     They
    0.98
    POSITIVE LOGITS
    ని
    1.26
    2
    1.05
    т
    1.04
     agreg
    1.01
     structs
    1.01
     integrals
    0.98
    ва
    0.98
     altres
    0.98
     simplices
    0.96
     compris
    0.95
    Activations Density 0.000%

    No Known Activations