© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 146
    Prev
    Next
    INDEX
    Explanations

    Level numbers or chapter numbers

    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
     rain
    1.00
    雨
    0.93
     Rain
    0.92
     rainy
    0.91
     lluvia
    0.89
     rains
    0.88
    Rain
    0.87
     raining
    0.86
     wet
    0.85
     Rainy
    0.84
    POSITIVE LOGITS
    manufacturing
    0.40
     आईसी
    0.37
     IQ
    0.36
    碘
    0.36
     SPM
    0.36
     cracked
    0.35
    आईसी
    0.35
     manufacturing
    0.35
     Transvaal
    0.35
     caloric
    0.35
    Activations Density 0.016%

    No Known Activations