© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11120
    Prev
    Next
    INDEX
    Explanations

    atom

    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
    を図
    0.51
    的分
    0.51
     த
    0.50
    会导致
    0.50
     biztons
    0.49
    ழிப்பு
    0.48
    St
    0.47
     ದ
    0.47
    כים
    0.47
    afin
    0.47
    POSITIVE LOGITS
     Pere
    0.55
     anum
    0.54
     meu
    0.53
     Waiver
    0.53
    ک
    0.52
     её
    0.51
     Matte
    0.50
    윈
    0.50
     Anastasia
    0.49
     내가
    0.49
    Activations Density 0.005%

    No Known Activations