© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257653
    Prev
    Next
    INDEX
    Explanations

    full set

    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_22_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
    प
    0.30
     Options
    0.28
    /)
    0.28
     onward
    0.28
    (),
    0.27
    ()]
    0.27
     நாட்ட
    0.27
     L
    0.26
     former
    0.26
     Norway
    0.26
    POSITIVE LOGITS
    ᓵ
    0.39
    ﾇ
    0.34
     ожида
    0.34
     whaka
    0.33
    цей
    0.33
     reinado
    0.33
     популација
    0.33
    वेश
    0.33
     осталось
    0.33
     остав
    0.33
    Activations Density 0.001%

    No Known Activations