© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16693
    Prev
    Next
    INDEX
    Explanations

    dried, withered, or embalmed

    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_34_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
    警察
    0.47
     पुलिस
    0.43
     পুলিশ
    0.43
    police
    0.42
     പോലീസ്
    0.41
     NYPD
    0.40
    aisseur
    0.38
    🚓
    0.38
    पुलिस
    0.38
     경찰
    0.38
    POSITIVE LOGITS
     embal
    0.57
     drying
    0.56
     dried
    0.55
    dried
    0.54
     dries
    0.51
     withered
    0.51
    Dried
    0.50
     dry
    0.47
    embal
    0.47
     kering
    0.46
    Activations Density 0.022%

    No Known Activations