© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96739
    Prev
    Next
    INDEX
    Explanations

    atoms, molecules, chains

    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
     ]
    0.54
     thousand
    0.53
     b
    0.52
    TI
    0.52
    March
    0.52
     फिश
    0.51
     graph
    0.50
     tunnel
    0.49
     yourself
    0.49
     race
    0.49
    POSITIVE LOGITS
    linebreak
    0.50
    雅黑
    0.46
    adecimal
    0.45
    دايه
    0.45
     dilaksanakan
    0.45
    ুখী
    0.44
    
    0.44
    емые
    0.44
    ˌ
    0.44
    ্ধ
    0.43
    Activations Density 0.011%

    No Known Activations