© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213474
    Prev
    Next
    INDEX
    Explanations

    bl/ble sounds

    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_50_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
     me
    0.50
     재
    0.49
     colis
    0.47
     Me
    0.47
    me
    0.46
    Me
    0.46
     mols
    0.46
     Re
    0.45
    ME
    0.45
    재
    0.43
    POSITIVE LOGITS
    Ble
    0.61
     בל
    0.59
     블
    0.59
     bl
    0.58
    Bl
    0.57
     Ble
    0.57
     ब्ले
    0.57
     بل
    0.56
    kry
    0.56
     ক্র
    0.54
    Activations Density 0.028%

    No Known Activations