© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49611
    Prev
    Next
    INDEX
    Explanations

    crossing signals or danger

    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_31_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
    ໜ
    0.41
     ढ
    0.41
     Rain
    0.39
     tamb
    0.39
     Alejandro
    0.39
     Zo
    0.38
     lluvias
    0.37
     memas
    0.37
    ymmetries
    0.36
    ர்க
    0.36
    POSITIVE LOGITS
    ប៉ុ
    0.48
    Crossing
    0.47
    折
    0.40
     crossings
    0.39
    Epic
    0.38
    ᅴ
    0.38
    測試
    0.38
    ап
    0.38
     कैलाश
    0.37
    홧
    0.37
    Activations Density 0.015%

    No Known Activations