© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32618
    Prev
    Next
    INDEX
    Explanations

    Finnish language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ma
    0.50
     Maa
    0.49
     Ma
    0.47
    Ma
    0.45
    NK
    0.45
     rank
    0.43
    <0x90>
    0.42
    Men
    0.42
     마
    0.41
     PMA
    0.41
    POSITIVE LOGITS
     টাই
    0.47
     लाइ
    0.44
     ട
    0.41
     टाइ
    0.41
     Su
    0.39
     타이
    0.39
     ਟ
    0.38
     تای
    0.38
     pe
    0.38
    Per
    0.38
    Activations Density 0.001%

    No Known Activations