© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78681
    Prev
    Next
    INDEX
    Explanations

    mer merchandising

    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_53_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
    Mp
    0.48
     Meh
    0.46
     m
    0.46
     age
    0.46
     Maha
    0.45
     الدوره
    0.45
    Meh
    0.45
    mp
    0.43
    Age
    0.43
    𝑫
    0.43
    POSITIVE LOGITS
     mer
    0.59
     Mer
    0.58
    mer
    0.55
    メル
    0.52
     תח
    0.52
    Mer
    0.49
     merchandising
    0.48
     MER
    0.48
    MER
    0.47
     मेर
    0.46
    Activations Density 0.000%

    No Known Activations