© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43739
    Prev
    Next
    INDEX
    Explanations

    -ness suffixes

    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_13_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
     cartas
    0.49
     }+
    0.48
     સર્
    0.47
     beneficia
    0.47
     让
    0.47
     बाला
    0.46
    妵
    0.46
     अस्त
    0.45
     }.
    0.45
     separa
    0.45
    POSITIVE LOGITS
    i
    0.70
    \
    0.61
    is
    0.57
    ي
    0.55
    Amazon
    0.54
    BMP
    0.53
    Shannon
    0.52
    spring
    0.49
     GDP
    0.49
    GDP
    0.48
    Activations Density 0.002%

    No Known Activations