© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9551
    Prev
    Next
    INDEX
    Explanations

    that's "

    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
     *
    0.20
     THEIR
    0.19
    Their
    0.17
     Their
    0.17
     *,
    0.17
     deres
    0.16
     '*'
    0.16
    他們的
    0.16
    their
    0.16
     *_
    0.16
    POSITIVE LOGITS
     đó
    0.28
    thats
    0.24
     thats
    0.24
    それが
    0.24
    Thats
    0.23
     ذلك
    0.20
     Thats
    0.20
    それは
    0.19
     Đó
    0.19
     itu
    0.19
    Activations Density 0.092%

    No Known Activations