© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170236
    Prev
    Next
    INDEX
    Explanations

    union

    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_56_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
    cup
    0.76
     cup
    0.73
    Cup
    0.64
     Cup
    0.64
     杯
    0.54
     cups
    0.54
     CUP
    0.52
    杯
    0.50
     союз
    0.50
     Cups
    0.46
    POSITIVE LOGITS
     Un
    2.52
    Un
    2.39
     un
    1.96
    un
    1.84
     uni
    1.64
     Uni
    1.59
     уни
    1.43
    Uni
    1.40
    uni
    1.30
    btnUn
    1.30
    Activations Density 0.008%

    No Known Activations