© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235015
    Prev
    Next
    INDEX
    Explanations

    cleaning text removing punctuation lowercase

    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_32_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
     Melissa
    0.40
    谿
    0.39
     MLC
    0.36
     Estelle
    0.36
    ttp
    0.36
     Mell
    0.35
     Qualified
    0.35
     Acoustic
    0.35
    歿
    0.35
    Melissa
    0.35
    POSITIVE LOGITS
     goose
    0.42
     helplessly
    0.40
     assaulted
    0.40
     assaulting
    0.38
     हादसे
    0.38
    ното
    0.37
    끓
    0.37
    UPD
    0.37
    OnError
    0.37
     égale
    0.37
    Activations Density 0.001%

    No Known Activations