© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203049
    Prev
    Next
    INDEX
    Explanations

    ear

    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_46_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
    USTOM
    0.46
    neg
    0.42
     bine
    0.42
    佺
    0.40
    Substring
    0.38
    btnUn
    0.38
     Pupp
    0.38
     WELL
    0.37
     Wy
    0.37
    isco
    0.37
    POSITIVE LOGITS
    Ear
    0.75
     ear
    0.69
     Ear
    0.68
    耳
    0.60
     कान
    0.59
    ears
    0.57
     ears
    0.57
     耳
    0.55
    耳朵
    0.55
     Ears
    0.54
    Activations Density 0.002%

    No Known Activations