© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195900
    Prev
    Next
    INDEX
    Explanations

    data processing or execution instructions

    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_27_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
     телевиде
    0.38
    television
    0.37
    까
    0.36
    诽
    0.36
    '+
    0.36
     картин
    0.36
    かせ
    0.36
    acağını
    0.35
    (){}
    0.35
    '):
    0.35
    POSITIVE LOGITS
     Pooling
    0.39
    ys
    0.38
     Prag
    0.38
     realistically
    0.37
     Pools
    0.37
    Pool
    0.35
     individually
    0.35
     Pool
    0.35
     Establishing
    0.35
    र्‍या
    0.35
    Activations Density 0.001%

    No Known Activations