© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121347
    Prev
    Next
    INDEX
    Explanations

    supply and demand match

    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_27_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
     dosimetry
    0.42
    阚
    0.41
    veille
    0.39
    제곱
    0.38
    辐射
    0.37
     Biele
    0.37
     ADC
    0.37
    的关键
    0.36
     MyBatis
    0.36
    嘧
    0.36
    POSITIVE LOGITS
     outflows
    0.42
    zoom
    0.42
     chứng
    0.41
    offs
    0.40
    araan
    0.40
    purpose
    0.40
    ights
    0.39
     elevators
    0.39
    ats
    0.39
     artificially
    0.39
    Activations Density 0.071%

    No Known Activations