© 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. 162408
    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
                    
    0.79
    Y
    0.75
    它
    0.74
    )-\
    0.71
    자는
    0.68
     significativas
    0.68
    르게
    0.66
     phận
    0.66
    \}}
    0.65
    geordnet
    0.65
    POSITIVE LOGITS
    s
    1.16
    e
    0.88
    ↵
    0.86
    ene
    0.83
    د
    0.78
    ير
    0.77
    esk
    0.73
    बोर्ड
    0.71
    س
    0.71
    ies
    0.70
    Activations Density 0.000%

    No Known Activations