© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62548
    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_2_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
    ков
    0.94
    もら
    0.91
    いますが
    0.88
    یی
    0.84
     necessario
    0.84
     усі
    0.81
    ﺗ
    0.81
     samoglas
    0.77
     pakas
    0.77
     основ
    0.76
    POSITIVE LOGITS
     was
    1.58
    on
    1.27
    á
    1.11
    is
    1.05
     for
    0.98
    was
    0.98
     and
    0.97
     is
    0.97
     has
    0.96
     on
    0.94
    Activations Density 0.000%

    No Known Activations