© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215161
    Prev
    Next
    INDEX
    Explanations

    loading files or code examples

    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_16_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
     Makers
    0.48
     voted
    0.46
     Principles
    0.45
    ត្រូវការ
    0.44
     elecciones
    0.44
    是對
    0.44
     Prinzip
    0.44
    绡
    0.43
    ➨
    0.43
    ెండు
    0.43
    POSITIVE LOGITS
    rove
    0.47
    ud
    0.47
     inquis
    0.42
     dönüş
    0.42
    িরে
    0.41
    чено
    0.41
    ulum
    0.40
    अभ
    0.39
    вра
    0.39
    んですよ
    0.39
    Activations Density 0.000%

    No Known Activations