© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43973
    Prev
    Next
    INDEX
    Explanations

    non-profit organization

    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
    Bla
    0.44
     Projection
    0.43
     Bla
    0.43
    🫐
    0.43
     двор
    0.43
     ఎ
    0.42
    旄
    0.41
     smě
    0.41
    明确
    0.41
     করিতেছেন
    0.41
    POSITIVE LOGITS
    ரான
    0.45
     midfield
    0.43
    lamydia
    0.39
    ばかり
    0.37
    никова
    0.37
     सिन्हा
    0.37
    ár
    0.37
     Wikipedia
    0.37
     í
    0.36
     Wiesbaden
    0.36
    Activations Density 0.001%

    No Known Activations