© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213910
    Prev
    Next
    INDEX
    Explanations

    other [noun/adjective]

    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_5_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
    ться
    1.24
    ление
    1.18
    (
    1.13
    し
    1.09
    є
    1.09
    .
    1.08
    ู
    1.03
    ления
    1.02
    τή
    1.02
    ig
    1.00
    POSITIVE LOGITS
     économ
    1.28
     ancienne
    1.28
    મ
    1.28
    ب
    1.27
     allemand
    1.26
     équipes
    1.23
     it
    1.23
     œuvres
    1.23
     opérations
    1.22
    nor
    1.20
    Activations Density 0.005%

    No Known Activations