© 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. 208662
    Prev
    Next
    INDEX
    Explanations

    hear

    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
    ୍କ
    0.40
    ⃙
    0.38
    ოს
    0.37
    hala
    0.34
    обс
    0.34
    釭
    0.34
    jel
    0.33
    odnik
    0.32
    섣
    0.32
     તરી
    0.32
    POSITIVE LOGITS
     hear
    3.11
    Hear
    3.00
     Hear
    2.94
     hears
    2.91
     heard
    2.86
    hear
    2.77
     hearing
    2.72
     Hearing
    2.53
    heard
    2.53
     слы
    2.52
    Activations Density 0.017%

    No Known Activations