© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5483
    Prev
    Next
    INDEX
    Explanations

    react jsx code

    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
    避
    0.42
     Luisa
    0.40
     Rif
    0.38
    ɽ
    0.37
    ulière
    0.36
    nels
    0.35
     König
    0.35
     Erdoğan
    0.34
    rif
    0.34
    قان
    0.34
    POSITIVE LOGITS
    functional
    0.47
     functional
    0.45
     функциона
    0.42
     Functional
    0.41
    Functional
    0.41
    袜子
    0.37
    膀
    0.37
    䘚
    0.37
     stool
    0.37
    靶
    0.37
    Activations Density 0.005%

    No Known Activations