© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15360
    Prev
    Next
    INDEX
    Explanations

    negative numbers or words

    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_40_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
     ple
    0.41
     PLE
    0.36
     дом
    0.35
     Rei
    0.35
     lumped
    0.35
     Chub
    0.35
    oush
    0.34
    }}{|
    0.34
     कमे
    0.33
    ின்ற
    0.33
    POSITIVE LOGITS
     negative
    1.17
    negative
    1.13
     Negative
    1.10
    Negative
    1.09
     negat
    0.99
     negativo
    0.97
     negativ
    0.96
     нега
    0.95
    负
    0.95
     negatif
    0.95
    Activations Density 0.017%

    No Known Activations