© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16955
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and comparisons

    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_40_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
    曱
    0.20
     Princess
    0.19
    ğaz
    0.18
     clung
    0.18
    adres
    0.18
     positi
    0.18
     }}=
    0.18
     অপ
    0.18
    άζ
    0.18
     puzz
    0.17
    POSITIVE LOGITS
     Browne
    0.18
    Hfn
    0.18
     Vermeer
    0.17
    scaler
    0.17
    Scal
    0.17
     scott
    0.17
    alien
    0.16
    ларни
    0.16
     scattered
    0.16
    検索
    0.16
    Activations Density 0.007%

    No Known Activations