© 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. 143236
    Prev
    Next
    INDEX
    Explanations

    interact or treat

    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
     تفصیل
    0.39
     gemacht
    0.38
     radially
    0.38
     подро
    0.37
     maintained
    0.37
    maintained
    0.35
    별
    0.35
     ආහාර
    0.35
     finding
    0.34
     mant
    0.34
    POSITIVE LOGITS
    fol
    0.43
     Never
    0.42
    Showing
    0.41
     montré
    0.40
    ंदा
    0.40
     Shown
    0.40
    Show
    0.39
    Hover
    0.39
    鄢
    0.39
     Show
    0.39
    Activations Density 0.004%

    No Known Activations