© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4008
    Prev
    Next
    INDEX
    Explanations

    model

    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_40_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
    pie
    0.39
     pets
    0.37
     atm
    0.37
     ზ
    0.37
     ATM
    0.37
     ох
    0.36
    ('').
    0.36
    atm
    0.36
    mp
    0.35
     море
    0.35
    POSITIVE LOGITS
    தலை
    0.41
     noticia
    0.40
     Triumph
    0.39
     noticias
    0.36
     luck
    0.36
     Giul
    0.36
    /"+
    0.36
     grabando
    0.35
     کھیلنے
    0.35
    亵
    0.35
    Activations Density 0.070%

    No Known Activations