© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59339
    Prev
    Next
    INDEX
    Explanations

    desired

    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_11_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
    ي
    0.55
    P
    0.51
    T
    0.49
    /*
    0.48
    a
    0.48
    .
    0.46
    ফ
    0.45
    0.44
     piz
    0.43
    。
    0.43
    POSITIVE LOGITS
     හො
    0.56
     ရှိ
    0.56
    Globals
    0.55
    𐰼
    0.55
    𒊑
    0.54
    UnderWater
    0.53
    rigley
    0.52
    året
    0.52
     еже
    0.52
     வித்தியாச
    0.51
    Activations Density 0.000%

    No Known Activations