© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197893
    Prev
    Next
    INDEX
    Explanations

    teaching something

    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_15_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
    '
    0.50
    de
    0.49
    da
    0.48
     de
    0.47
    te
    0.46
     prequel
    0.46
    ته
    0.46
     bestseller
    0.44
    taining
    0.44
    dt
    0.43
    POSITIVE LOGITS
     Drafting
    0.51
     極
    0.49
     Está
    0.47
     Putra
    0.47
    телем
    0.47
     Đầu
    0.46
     Identifying
    0.45
     乀
    0.45
     ಮತ್ತು
    0.45
     Más
    0.45
    Activations Density 0.000%

    No Known Activations