© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28067
    Prev
    Next
    INDEX
    Explanations

    hiding places and hidden damage

    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_10_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
    خ
    0.26
    ط
    0.26
    لا
    0.25
    ט
    0.25
    ير
    0.23
    را
    0.22
    ق
    0.22
    ਰ
    0.22
    три
    0.22
    {
    0.22
    POSITIVE LOGITS
    erà
    0.21
    enin
    0.20
    anın
    0.20
    .\"
    0.20
     yù
    0.20
     і
    0.20
    EOUS
    0.19
     vì
    0.19
    ELI
    0.19
     khỏi
    0.19
    Activations Density 0.008%

    No Known Activations