© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62728
    Prev
    Next
    INDEX
    Explanations

    e-commerce sites and brands

    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_41_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
    watermelon
    0.44
    cida
    0.40
     வெங்க
    0.40
    alian
    0.40
    yellow
    0.38
    qid
    0.38
    猕
    0.38
    Seller
    0.37
    Yellow
    0.37
    ^[
    0.37
    POSITIVE LOGITS
    }$&$-
    0.39
     Este
    0.38
    },-\
    0.37
     É
    0.36
    هار
    0.36
     Handy
    0.36
    甭
    0.36
    }}-\
    0.35
     #{
    0.35
     Helm
    0.35
    Activations Density 0.004%

    No Known Activations