© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16857
    Prev
    Next
    INDEX
    Explanations

    to

    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_15_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
    PSD
    0.30
    acy
    0.29
    chak
    0.29
    arel
    0.28
    iri
    0.27
    descriptions
    0.27
    t
    0.27
    í
    0.26
    iring
    0.26
    IT
    0.26
    POSITIVE LOGITS
     acesta
    0.32
     hayvan
    0.31
     Russie
    0.30
     vaisseaux
    0.28
     GLASS
    0.28
     vasculaire
    0.28
     megfelel
    0.28
     değerli
    0.28
    ゥム
    0.28
     merkezi
    0.28
    Activations Density 0.178%

    No Known Activations