© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138846
    Prev
    Next
    INDEX
    Explanations

    laws and regulations

    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_37_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
    Conservation
    0.40
     conserva
    0.39
     conservar
    0.39
    璫
    0.39
     เดียว
    0.38
     сохрани
    0.38
    conservation
    0.38
     hayvan
    0.37
    इसे
    0.37
    фом
    0.37
    POSITIVE LOGITS
     nonzero
    0.46
    ídos
    0.44
     nonresident
    0.43
     Fibonacci
    0.42
     medical
    0.42
     wellness
    0.41
     residency
    0.41
     industrious
    0.40
    伤
    0.40
     boot
    0.39
    Activations Density 0.000%

    No Known Activations