© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52188
    Prev
    Next
    INDEX
    Explanations

    any

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    very
    0.51
     very
    0.51
     Next
    0.46
     next
    0.45
     ways
    0.42
    咬
    0.41
    ̑
    0.41
     дуже
    0.41
    otros
    0.40
     mycket
    0.39
    POSITIVE LOGITS
    Either
    0.54
    either
    0.50
    Numerous
    0.48
     Either
    0.48
     either
    0.47
    Hundreds
    0.43
    砺
    0.41
    也不知道
    0.39
    Poll
    0.38
     sizeable
    0.38
    Activations Density 0.002%

    No Known Activations