© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137625
    Prev
    Next
    INDEX
    Explanations

    audio content

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Liter
    0.52
    liter
    0.46
     літера
    0.44
     littérature
    0.44
     liter
    0.44
    缸
    0.43
     olor
    0.42
     ላ
    0.41
     இலக்கிய
    0.41
     literatura
    0.41
    POSITIVE LOGITS
    Practical
    0.48
    ▆
    0.41
     Practical
    0.40
    补
    0.40
    ractical
    0.40
    Listen
    0.38
     practical
    0.38
     listen
    0.38
    Trans
    0.37
    ActionListener
    0.37
    Activations Density 0.002%

    No Known Activations