© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213440
    Prev
    Next
    INDEX
    Explanations

    scoring goals

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    ],"
    0.43
     ইনফ
    0.42
    phys
    0.41
     haz
    0.40
    ুইস
    0.40
     QI
    0.40
    Snap
    0.39
     Cep
    0.39
     hz
    0.39
     displace
    0.39
    POSITIVE LOGITS
    Читать
    0.48
    苔
    0.41
    utzt
    0.38
    веден
    0.36
     ROCK
    0.36
     स्क्रब
    0.36
     semangat
    0.35
     рок
    0.35
     contemporary
    0.35
    年は
    0.35
    Activations Density 0.001%

    No Known Activations