© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61848
    Prev
    Next
    INDEX
    Explanations

    merit

    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_59_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
    십시오
    0.38
     aqua
    0.35
     alkali
    0.33
     basketball
    0.32
    ocardial
    0.32
    ivate
    0.32
    <0x9C>
    0.32
     "../../
    0.32
     Alkali
    0.31
     hy
    0.31
    POSITIVE LOGITS
     merit
    3.19
     merits
    2.80
     Merit
    2.78
     mer
    2.34
    Mer
    2.20
     Mer
    2.09
     meritorious
    2.00
    mer
    1.97
     merito
    1.83
     मेर
    1.76
    Activations Density 0.038%

    No Known Activations