© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138520
    Prev
    Next
    INDEX
    Explanations

    machine element

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    uintes
    0.37
     castor
    0.36
     cast
    0.36
     rapidly
    0.36
    achal
    0.35
     rapidez
    0.35
    况
    0.34
    ορ
    0.34
     abras
    0.33
     كنا
    0.33
    POSITIVE LOGITS
    মনি
    0.42
     ELEMENT
    0.42
    感的
    0.42
    Machine
    0.41
    machine
    0.41
     عنصر
    0.40
    MACHINE
    0.40
    比利
    0.39
     elemento
    0.38
     үнд
    0.38
    Activations Density 0.004%

    No Known Activations