© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35166
    Prev
    Next
    INDEX
    Explanations

    another

    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_3_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
    сів
    0.74
     kteří
    0.67
     које
    0.64
    数据的
    0.64
    )*
    0.61
    数据集
    0.61
     giọng
    0.61
     daugiau
    0.60
    ல்
    0.60
     jejich
    0.60
    POSITIVE LOGITS
    t
    1.34
    ne
    0.95
    ৮
    0.82
    í
    0.81
     can
    0.80
    ONG
    0.80
    ৫
    0.80
    ă
    0.73
    ti
    0.72
    It
    0.71
    Activations Density 0.002%

    No Known Activations