© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31732
    Prev
    Next
    INDEX
    Explanations

    tricky because

    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_40_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
     चु
    0.41
    하게
    0.37
    Okno
    0.37
     मुताब
    0.37
     آنچه
    0.37
    ρώ
    0.36
    취
    0.36
     Đá
    0.36
    шибка
    0.35
    雬
    0.35
    POSITIVE LOGITS
     business
    0.40
    tense
    0.40
    mse
    0.39
     drilled
    0.37
    dependence
    0.37
     tense
    0.37
     drilling
    0.36
     biznes
    0.36
     drill
    0.36
     development
    0.36
    Activations Density 0.027%

    No Known Activations