© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207642
    Prev
    Next
    INDEX
    Explanations

    string type hint

    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_20_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
     Bew
    0.45
    ków
    0.43
    owo
    0.43
     предпоч
    0.42
    zení
    0.42
    ń
    0.41
    '")
    0.41
     Wren
    0.40
    nx
    0.40
    wski
    0.40
    POSITIVE LOGITS
     cet
    0.48
    өнья
    0.46
    મેન્ટ
    0.46
    规
    0.46
     terb
    0.44
     visas
    0.44
     quali
    0.43
    ఈ
    0.43
    犮
    0.43
     carbon
    0.42
    Activations Density 0.001%

    No Known Activations