© 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
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4651
    Prev
    Next
    INDEX
    Explanations

    model generating stories

    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_39_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
     visuals
    0.41
    称
    0.38
    িয়ে
    0.37
    ayscale
    0.37
     socialize
    0.36
     القيم
    0.36
     žmon
    0.36
    忔
    0.36
    ocial
    0.35
    ouville
    0.35
    POSITIVE LOGITS
    Collected
    0.40
    soluble
    0.39
     Collecting
    0.39
    Storage
    0.38
     collect
    0.37
     collecting
    0.37
    нибудь
    0.36
    ---’
    0.36
    収集
    0.36
     collected
    0.36
    Activations Density 0.053%

    No Known Activations