© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197822
    Prev
    Next
    INDEX
    Explanations

    blood

    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_46_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
     cellular
    0.42
     kip
    0.41
     cy
    0.39
     vessels
    0.39
    ＝＝
    0.39
     Vessel
    0.39
    ritual
    0.39
    痊
    0.38
     huyết
    0.38
    戻
    0.38
    POSITIVE LOGITS
    Dynamics
    0.42
     CENTERS
    0.40
     NAB
    0.39
     dynamics
    0.38
    仕様
    0.38
     BIN
    0.38
     फ्री
    0.38
     programs
    0.38
    PSA
    0.38
     केंद्रों
    0.37
    Activations Density 0.001%

    No Known Activations