© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134356
    Prev
    Next
    INDEX
    Explanations

    quantifier followed by noun

    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_37_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
    ők
    0.30
    loadConst
    0.28
    Académie
    0.26
    ");*/
    0.26
    lení
    0.26
     AOS
    0.26
    冈
    0.26
    …"
    0.25
     пов
    0.25
    கூ
    0.24
    POSITIVE LOGITS
     vegetable
    0.26
     dextrose
    0.26
     humiliating
    0.25
     javax
    0.24
     माइक्रोस
    0.24
     testclass
    0.23
     waitress
    0.23
     Hover
    0.23
    少なく
    0.23
     जवाहर
    0.23
    Activations Density 0.091%

    No Known Activations