© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228692
    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_6_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
     Strengthen
    1.05
    ;"
    1.00
    ،
    0.97
    пись
    0.89
     Insulation
    0.85
    ඃ
    0.84
    }}$
    0.82
    ፣
    0.82
    *,
    0.81
     Receivable
    0.80
    POSITIVE LOGITS
    the
    0.92
    的
    0.87
    не
    0.83
    ين
    0.81
    ной
    0.81
    u
    0.79
    s
    0.78
    f
    0.76
    ्य
    0.75
    ב
    0.75
    Activations Density 0.000%

    No Known Activations