© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177867
    Prev
    Next
    INDEX
    Explanations

    loan amounts

    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_24_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
     means
    0.34
     측
    0.34
     longtime
    0.34
     tightness
    0.33
     Basil
    0.33
     Min
    0.32
     mounts
    0.32
     shuffled
    0.32
     shuffling
    0.32
     long
    0.32
    POSITIVE LOGITS
     sampai
    0.40
    𝒔
    0.38
     रिप्रोडक्शन
    0.38
     segundo
    0.37
    RetResult
    0.37
     sujeto
    0.37
    inerja
    0.37
    微软雅黑
    0.37
    خواهد
    0.37
     fünf
    0.37
    Activations Density 0.000%

    No Known Activations