© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30316
    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_7_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
    0.84
     prototypes
    0.74
     secretaries
    0.72
     impediments
    0.70
     cylinders
    0.70
     passwords
    0.69
     vapors
    0.69
     exemplaires
    0.68
     delicacies
    0.67
     vacuoles
    0.67
    POSITIVE LOGITS
    is
    0.86
    a
    0.82
    id
    0.81
    set
    0.80
     Bình
    0.79
    mrow
    0.77
    ing
    0.75
    it
    0.73
    num
    0.73
    kit
    0.72
    Activations Density 0.000%

    No Known Activations