© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206252
    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_37_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
    ].)
    0.41
     இருக்கிறது
    0.39
     रहती
    0.37
    יש
    0.36
     небольшой
    0.35
    Ẓ
    0.35
     रहता
    0.34
    িয়৷
    0.34
     जनवरी
    0.34
    })(\
    0.34
    POSITIVE LOGITS
    DEFINE
    0.40
    isek
    0.39
     restre
    0.38
    folk
    0.37
     pared
    0.37
    োস
    0.37
     erster
    0.37
     onde
    0.37
    älte
    0.36
     excl
    0.36
    Activations Density 0.000%

    No Known Activations