© 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. 96633
    Prev
    Next
    INDEX
    Explanations

    ding

    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
    мана
    0.52
     adenosine
    0.52
    рожден
    0.52
    ্ি
    0.49
    ্ভ
    0.48
    โยชน์
    0.48
     பயன
    0.48
    Ⲥ
    0.47
     zwią
    0.47
    Ṕ
    0.46
    POSITIVE LOGITS
    wei
    0.54
     आदेश
    0.49
     itineraries
    0.47
     regrets
    0.47
    ীল
    0.45
     -*-
    0.45
    itty
    0.44
    i
    0.44
    ོ་
    0.44
     विनय
    0.43
    Activations Density 0.000%

    No Known Activations