© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100073
    Prev
    Next
    INDEX
    Explanations

    voicings

    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_14_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
    ofd
    0.61
     פון
    0.60
    ধ্যে
    0.59
    >\<^
    0.59
     श्रेणी
    0.59
    inture
    0.58
    emd
    0.57
     распространен
    0.57
    olev
    0.57
     හේ
    0.57
    POSITIVE LOGITS
     cables
    0.59
    <0x0D>
    0.57
     to
    0.57
          
    0.53
                           
    0.53
             
    0.51
     cable
    0.50
     potentiometer
    0.49
     TEL
    0.48
    0.47
    Activations Density 0.000%

    No Known Activations