© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    modeling clay and shadows

    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
     itemprop
    0.21
     curators
    0.21
     repar
    0.21
    imbus
    0.20
    itches
    0.20
    ंख्य
    0.20
    ｲ
    0.20
    ocument
    0.20
    ರೆಯ
    0.20
     europ
    0.20
    POSITIVE LOGITS
     sources
    0.26
     absorb
    0.24
     Sources
    0.24
    磁
    0.23
     kaynak
    0.23
    magnetic
    0.23
     magnetic
    0.23
    sources
    0.23
    sor
    0.22
     magnetized
    0.22
    Activations Density 0.000%

    No Known Activations