© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20274
    Prev
    Next
    INDEX
    Explanations

    humming

    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
    ohan
    0.42
    Gav
    0.37
    zī
    0.37
    ടു
    0.37
    ecal
    0.36
    ovis
    0.36
    SqlDbType
    0.35
    懇
    0.35
     गिर
    0.35
    zz
    0.35
    POSITIVE LOGITS
     hum
    3.45
    Hum
    2.78
     Hum
    2.77
    hum
    2.67
     humming
    2.56
     HUM
    2.45
     Humming
    2.11
    HUM
    1.98
    哼
    1.91
     Humphrey
    1.80
    Activations Density 0.082%

    No Known Activations