© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165004
    Prev
    Next
    INDEX
    Explanations

    first time periods

    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_13_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
     vote
    0.55
    R
    0.54
    U
    0.54
    )
    0.52
    I
    0.52
    C
    0.52
    Si
    0.51
    T
    0.51
    F
    0.51
    [
    0.51
    POSITIVE LOGITS
     obstáculos
    0.56
    édi
    0.49
     Après
    0.48
    стить
    0.47
     After
    0.46
     During
    0.46
    íamos
    0.45
    msp
    0.45
    魃
    0.45
    теп
    0.45
    Activations Density 0.038%

    No Known Activations