© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88539
    Prev
    Next
    INDEX
    Explanations

    Neoclassical style and instruments act

    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_3_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
    am
    0.75
    W
    0.73
    lü
    0.72
    meler
    0.72
    ו
    0.70
    lf
    0.70
    T
    0.70
    V
    0.68
    Q
    0.68
    lara
    0.65
    POSITIVE LOGITS
    я
    0.83
    ై
    0.80
     are
    0.73
     according
    0.71
    ί
    0.70
     explained
    0.69
    นะ
    0.68
    ма
    0.65
     escaped
    0.64
     innocent
    0.64
    Activations Density 0.000%

    No Known Activations