© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205375
    Prev
    Next
    INDEX
    Explanations

    manufacturing processes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    就
    0.84
    ري
    0.82
     جميع
    0.81
     wymag
    0.80
    LE
    0.79
     synchron
    0.78
     fallback
    0.78
     spust
    0.78
     forgo
    0.77
     brauch
    0.77
    POSITIVE LOGITS
    ilibrium
    0.98
    ks
    0.97
    ines
    0.97
    '
    0.93
    itation
    0.91
    cles
    0.90
    ow
    0.89
    cer
    0.89
    ptic
    0.89
    ors
    0.89
    Activations Density 0.001%

    No Known Activations