© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204188
    Prev
    Next
    INDEX
    Explanations

    actor followed by system or framework

    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
     can
    1.24
     is
    1.14
     are
    1.05
     as
    1.02
    f
    0.90
     regressions
    0.89
     has
    0.86
     arise
    0.86
     bevel
    0.86
     generalize
    0.84
    POSITIVE LOGITS
    ur
    1.14
    overwrite
    1.09
    ó
    1.09
    us
    1.08
     Ně
    1.05
    to
    1.04
    ست
    1.02
    াস
    1.02
    ari
    1.00
     Прави
    0.97
    Activations Density 0.001%

    No Known Activations