© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38204
    Prev
    Next
    INDEX
    Explanations

    "re" sound endings

    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_57_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
    asha
    0.57
    ﺍ
    0.57
    𝔞
    0.56
    ας
    0.55
    ajes
    0.55
    აბ
    0.55
    а
    0.55
    az
    0.55
    𝐚
    0.55
    𝓪
    0.54
    POSITIVE LOGITS
     фа
    0.58
    ฟา
    0.54
    REE
    0.52
    ree
    0.52
    RED
    0.50
    ruire
    0.50
     FAX
    0.49
    рее
    0.49
    reed
    0.48
    ru
    0.48
    Activations Density 0.021%

    No Known Activations