© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140228
    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_12_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
     ܠ
    0.68
     של
    0.62
     но
    0.60
     የ
    0.60
     없
    0.59
     את
    0.59
     የማ
    0.59
     dalších
    0.58
     항
    0.57
     별
    0.57
    POSITIVE LOGITS
    I
    0.55
    Plain
    0.53
    V
    0.53
    ंभ
    0.53
    Signs
    0.53
    Serum
    0.51
    F
    0.51
    plain
    0.50
    Slim
    0.50
    Guest
    0.50
    Activations Density 0.000%

    No Known Activations