© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43175
    Prev
    Next
    INDEX
    Explanations

    if you

    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_22_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
    An
    0.42
    DW
    0.41
    Journal
    0.40
    Arch
    0.39
     Opportun
    0.39
     Arch
    0.39
    DLJ
    0.38
    安
    0.38
    Efficient
    0.37
    王朝
    0.37
    POSITIVE LOGITS
     ഉരു
    0.49
     contém
    0.45
     tumbuh
    0.44
     excludes
    0.43
     lamb
    0.41
    descricao
    0.41
     tambahan
    0.41
    ()/
    0.41
     descriptors
    0.41
     hyster
    0.41
    Activations Density 0.006%

    No Known Activations