© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65325
    Prev
    Next
    INDEX
    Explanations

    "ha" sound

    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_51_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
     M
    0.56
     tle
    0.44
     М
    0.43
     Kak
    0.42
     Kuch
    0.42
     Mh
    0.42
     Sach
    0.41
     Vac
    0.40
    ymen
    0.40
     Sar
    0.40
    POSITIVE LOGITS
     ха
    0.66
    ハ
    0.57
    哈
    0.57
    ха
    0.53
     Haas
    0.48
    하
    0.47
     하
    0.46
     몰
    0.46
    Haw
    0.45
    Ха
    0.45
    Activations Density 0.013%

    No Known Activations