© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152567
    Prev
    Next
    INDEX
    Explanations

    lists and instructions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     где
    0.46
    A
    0.46
     realizando
    0.42
     realizing
    0.42
     utilizando
    0.42
     dimana
    0.41
     explicando
    0.41
    According
    0.41
     according
    0.41
     mediante
    0.41
    POSITIVE LOGITS
    Ö
    0.72
     Such
    0.71
     Não
    0.66
     To
    0.65
    Ü
    0.64
     Ü
    0.63
     Not
    0.62
     Çok
    0.62
     Ö
    0.61
     Në
    0.61
    Activations Density 0.000%

    No Known Activations