© 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. 152936
    Prev
    Next
    INDEX
    Explanations

    Spanish

    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
    淉
    0.47
    และ
    0.46
     al
    0.43
    գ
    0.43
    gård
    0.40
    łki
    0.39
    ÇÕES
    0.38
    栉
    0.38
     और
    0.37
    дже
    0.37
    POSITIVE LOGITS
     считают
    0.64
     دارند
    0.63
     be
    0.62
     могут
    0.58
    Where
    0.57
     mají
    0.56
     Where
    0.56
     mogą
    0.55
     majú
    0.55
     έχουν
    0.55
    Activations Density 0.002%

    No Known Activations