© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195709
    Prev
    Next
    INDEX
    Explanations

    invention and method

    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_15_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
    )
    0.54
    </b>
    0.51
     dve
    0.50
     dvoj
    0.50
     essere
    0.50
     L
    0.49
     Surf
    0.49
     du
    0.47
     sailed
    0.47
    v
    0.46
    POSITIVE LOGITS
    äck
    0.60
    Plate
    0.54
    meal
    0.52
    ills
    0.52
    ICKEL
    0.50
     Всем
    0.50
    öff
    0.50
     --------");
    0.50
    oomla
    0.49
    ill
    0.48
    Activations Density 0.000%

    No Known Activations