© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9432
    Prev
    Next
    INDEX
    Explanations

    redux actions or optimizers

    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
     QRCode
    0.53
     astronomers
    0.51
     Uranus
    0.50
     MetaMask
    0.50
     Griffiths
    0.48
    ---’
    0.48
     मुख्यतः
    0.48
     llrp
    0.47
     屋
    0.47
     WLAN
    0.46
    POSITIVE LOGITS
     dalla
    0.48
    ical
    0.46
    ского
    0.45
     dedication
    0.42
     когда
    0.40
    US
    0.40
    ě
    0.40
     Según
    0.39
     unlabeled
    0.39
    шего
    0.39
    Activations Density 0.014%

    No Known Activations