© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117600
    Prev
    Next
    INDEX
    Explanations

    information, command, database entries

    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_27_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
     Luckily
    0.42
    Pero
    0.37
    es
    0.37
     തൊ
    0.36
    Before
    0.35
    Luckily
    0.35
    ☁
    0.35
    ബോ
    0.34
    Се
    0.34
    宮
    0.34
    POSITIVE LOGITS
     genomic
    0.44
     phen
    0.42
     mitochondrial
    0.41
     thymus
    0.41
     phenotypic
    0.41
     site
    0.40
     downstream
    0.39
    ्वान
    0.39
     phenomena
    0.39
     hepatic
    0.38
    Activations Density 0.000%

    No Known Activations