© 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. 211114
    Prev
    Next
    INDEX
    Explanations

    starting + noun/context

    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
    아
    1.09
     ﺍ
    0.99
    in
    0.98
     accompagn
    0.85
     afterthought
    0.82
     histoires
    0.82
     ancienne
    0.81
     accom
    0.81
     approbation
    0.81
    padă
    0.81
    POSITIVE LOGITS
    ed
    1.12
     on
    1.09
     for
    1.00
    3
    0.98
    ina
    0.96
    ET
    0.85
    s
    0.84
    ä
    0.84
    é
    0.81
     with
    0.79
    Activations Density 0.010%

    No Known Activations