© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245169
    Prev
    Next
    INDEX
    Explanations

    perception, object detection, sensors like radar

    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_40_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
     }}=
    0.45
    anç
    0.43
     Putting
    0.39
     दत्ता
    0.38
    쭐
    0.38
    }+{
    0.38
     Víctor
    0.38
     Science
    0.37
    roof
    0.36
    TestData
    0.36
    POSITIVE LOGITS
     المث
    0.42
     প্রস্ত
    0.42
    ចប់
    0.38
     algae
    0.38
     perception
    0.37
     cloudy
    0.37
     chloroplast
    0.37
    前方
    0.37
    ఠ
    0.37
     kant
    0.36
    Activations Density 0.002%

    No Known Activations