© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120538
    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_27_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
     ElevatedButton
    0.42
     Theme
    0.41
     HttpClient
    0.41
     Facebook
    0.40
    Facebook
    0.40
     Targeting
    0.40
     Slider
    0.40
    犮
    0.39
     істо
    0.39
     최대한
    0.39
    POSITIVE LOGITS
     naïve
    0.43
     espiritual
    0.42
    terr
    0.40
     naive
    0.38
     آخر
    0.38
     regreso
    0.36
     tube
    0.36
     inoc
    0.36
     extingu
    0.36
     nemen
    0.35
    Activations Density 0.000%

    No Known Activations