© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86622
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Alte
    0.66
     elef
    0.66
    z
    0.66
     Tento
    0.66
     I
    0.62
    ه
    0.61
    ע
    0.60
     lé
    0.60
     studenti
    0.60
     apopt
    0.59
    POSITIVE LOGITS
    laws
    0.73
    raised
    0.69
    media
    0.66
    n
    0.66
    mp
    0.66
    nity
    0.66
    beds
    0.65
    𝗻
    0.65
    capital
    0.65
    living
    0.65
    Activations Density 0.010%

    No Known Activations