© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    names ending in an, nan, wan, man

    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
    ानुसार
    0.37
    ი
    0.36
    ্তে
    0.36
    nienie
    0.36
     necessari
    0.34
    Statement
    0.34
    ामुळे
    0.33
    னு
    0.33
     aven
    0.33
    nung
    0.33
    POSITIVE LOGITS
    ्तर
    0.61
    ubhav
    0.51
    egra
    0.47
    ufact
    0.47
    坷
    0.47
    staande
    0.45
    vänd
    0.45
    ther
    0.44
    cho
    0.43
    thia
    0.42
    Activations Density 0.202%

    No Known Activations