© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79551
    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_0_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
    ல்
    1.44
    したので
    1.25
    rotic
    1.12
    ৬
    1.10
    них
    1.05
    estellt
    1.05
     seterusnya
    1.04
     불구하고
    1.04
    いです
    1.02
    ado
    1.02
    POSITIVE LOGITS
    ن
    2.55
     for
    1.98
    ش
    1.98
    a
    1.95
    س
    1.79
    علم
    1.78
    ه
    1.77
    for
    1.77
    ع
    1.74
     as
    1.73
    Activations Density 0.000%

    No Known Activations