© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54015
    Prev
    Next
    INDEX
    Explanations

    that's when

    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_30_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
     fascinating
    0.46
     quilting
    0.43
     Очень
    0.43
    非常
    0.42
     非常
    0.41
    anesulf
    0.41
     quint
    0.41
    𝗘
    0.40
     весьма
    0.40
     very
    0.39
    POSITIVE LOGITS
     आणि
    0.53
     ਅਤੇ
    0.47
     এবং
    0.45
     thiab
    0.44
     agus
    0.43
     සහ
    0.43
     ۽
    0.43
    そして
    0.42
     그리고
    0.42
     और
    0.42
    Activations Density 0.003%

    No Known Activations