© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210616
    Prev
    Next
    INDEX
    Explanations

    lot of / lot to

    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_5_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
     o
    1.19
     nods
    1.14
     isotopes
    1.13
     ajustes
    1.10
     jogs
    1.10
     integrals
    1.09
    एम
    1.08
     averages
    1.08
     lures
    1.06
    A
    1.06
    POSITIVE LOGITS
    t
    1.59
    ↵
    1.24
    al
    1.09
    이다
    1.09
    of
    1.08
    σ
    1.02
    น
    0.96
     of
    0.96
    و
    0.92
    ció
    0.89
    Activations Density 0.001%

    No Known Activations