© 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. 144873
    Prev
    Next
    INDEX
    Explanations

    whatsapp, wafers

    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
    ad
    1.49
    นิด
    1.41
    ა
    1.39
    와의
    1.38
    the
    1.34
    ین
    1.34
    ینگ
    1.34
    ینده
    1.32
    기와
    1.27
    नं
    1.25
    POSITIVE LOGITS
     of
    2.02
     to
    1.82
     on
    1.78
    ך
    1.65
    d
    1.46
    ка
    1.41
     that
    1.34
    。
    1.27
    ).
    1.26
     I
    1.23
    Activations Density 0.000%

    No Known Activations