© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223474
    Prev
    Next
    INDEX
    Explanations

    tonkatsu, thylakoids, qazaq taxi

    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_10_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
     هاکي
    0.71
    ယာ
    0.68
     cataly
    0.68
    dP
    0.68
    dport
    0.66
     প্রজাতির
    0.66
     Pltf
    0.64
    ၈
    0.64
     Algebras
    0.64
    ]$;
    0.64
    POSITIVE LOGITS
    as
    1.26
    is
    1.22
    л
    1.17
    in
    1.11
    on
    1.02
    ol
    0.99
    ación
    0.97
    ار
    0.96
    en
    0.96
    um
    0.95
    Activations Density 0.000%

    No Known Activations