© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 12129
    Prev
    Next
    INDEX
    Explanations

    impedance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    orette
    0.31
     architect
    0.30
    ዬ
    0.30
    的设计
    0.29
     д
    0.29
     laranja
    0.29
    ado
    0.29
     ligaments
    0.29
    ibel
    0.28
    igan
    0.28
    POSITIVE LOGITS
     ISM
    0.31
    javase
    0.31
    remote
    0.30
    ക്കുന്ന
    0.29
    capac
    0.29
     ойнотуу
    0.29
     IMS
    0.28
     Bahadur
    0.28
     $*
    0.28
     Australien
    0.28
    Activations Density 0.021%

    No Known Activations