© 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. 62511
    Prev
    Next
    INDEX
    Explanations

    just followed by a verb

    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
    ?
    1.49
     and
    1.37
     B
    1.30
     A
    1.27
    on
    1.25
     J
    1.22
     a
    1.20
     D
    1.12
     I
    1.09
     $
    1.09
    POSITIVE LOGITS
    在
    1.20
    )’
    1.09
    도
    1.08
     in
    1.05
     در
    1.05
    기
    1.05
     মিন
    0.99
    ड
    0.99
    ۶
    0.98
    )"))
    0.96
    Activations Density 0.003%

    No Known Activations