© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198564
    Prev
    Next
    INDEX
    Explanations

    acquisition, cross-sections, data

    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_15_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
     frio
    0.13
    ;}
    0.13
     Cull
    0.12
    द्वार
    0.12
     деву
    0.11
     कॉलेजों
    0.11
     articoli
    0.11
     Coss
    0.11
    et
    0.11
     сообщения
    0.11
    POSITIVE LOGITS
    </h3>
    0.13
    तक
    0.12
     frameN
    0.12
     lineHeight
    0.12
    ة
    0.12
     BasicDBObject
    0.11
     viewDidLoad
    0.11
     لکھ
    0.11
     náz
    0.11
    ལ
    0.11
    Activations Density 0.006%

    No Known Activations