© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144649
    Prev
    Next
    INDEX
    Explanations

    sacred

    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_0_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
    те
    1.45
    ш
    1.35
    й
    1.34
    其他
    1.33
     entraîne
    1.33
    áme
    1.27
     tendencias
    1.27
    ä
    1.25
     különb
    1.23
     actualizaciones
    1.22
    POSITIVE LOGITS
    ↵
    1.80
    nın
    1.55
     to
    1.51
    k
    1.51
    2
    1.49
    _
    1.47
     is
    1.30
     not
    1.30
    0
    1.27
    to
    1.26
    Activations Density 0.000%

    No Known Activations