© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64936
    Prev
    Next
    INDEX
    Explanations

    hierarchy

    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
    늑
    0.38
     Gay
    0.38
    දන
    0.37
    တတ်
    0.37
     గణ
    0.36
     round
    0.36
    ρφ
    0.36
    ଉ
    0.36
     tig
    0.35
     Angles
    0.35
    POSITIVE LOGITS
     Hier
    3.52
    Hier
    3.47
     hierarchical
    3.44
     hier
    3.39
     hierarchy
    3.39
    hier
    3.33
     hierarch
    3.31
     Hierarchy
    3.25
     hierarchies
    3.22
    hierarchy
    3.14
    Activations Density 0.195%

    No Known Activations