© 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. 132763
    Prev
    Next
    INDEX
    Explanations

    portfolio discussion

    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
    る
    1.23
     lunar
    1.11
     microstructure
    1.03
    ت
    1.03
     metabolism
    0.98
     nymph
    0.98
    (
    0.98
    ᖕ
    0.97
     crust
    0.96
     multiplicative
    0.94
    POSITIVE LOGITS
     مؤرشف
    1.23
     Gosudarstvennyj
    1.16
    s
    1.15
     };
    1.08
     Elektrokh
    1.08
    th
    1.07
     Portail
    1.06
     História
    1.06
     Geschäftsführer
    1.05
     Loksatta
    1.02
    Activations Density 0.001%

    No Known Activations