© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246871
    Prev
    Next
    INDEX
    Explanations

    code definitions in python or swift

    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
     것은
    0.38
     тех
    0.38
    ematic
    0.37
     இருந்தால்
    0.37
     Boul
    0.36
    adə
    0.36
    걱
    0.33
    ilà
    0.32
    (;
    0.32
     Конгрегация
    0.32
    POSITIVE LOGITS
    Cities
    0.39
     algebraically
    0.36
    Ks
    0.36
    personen
    0.36
    Cast
    0.34
    اپنی
    0.34
     custodians
    0.33
     dajj
    0.33
     ko
    0.33
     wills
    0.33
    Activations Density 0.004%

    No Known Activations