© 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. 44958
    Prev
    Next
    INDEX
    Explanations

    to

    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
    al
    0.33
    es
    0.32
    am
    0.30
    d
    0.29
    ian
    0.28
    ia
    0.28
    ae
    0.28
    c
    0.26
    école
    0.25
    en
    0.25
    POSITIVE LOGITS
     येत
    0.27
    ז
    0.25
    ना
    0.24
     parab
    0.24
     slats
    0.24
     diastolic
    0.24
    ทาง
    0.23
     clinically
    0.23
     tachycardia
    0.23
     to
    0.23
    Activations Density 0.032%

    No Known Activations