© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60813
    Prev
    Next
    INDEX
    Explanations

    directed acyclic graph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
     प्रतिभाशाली
    0.57
    에게
    0.56
    }\
    0.55
     orijinal
    0.55
    お届け
    0.55
    Omega
    0.53
     बाहर
    0.50
     who
    0.50
    応答
    0.49
    }}^{*}\
    0.49
    POSITIVE LOGITS
    ate
    0.61
    inodes
    0.59
    atenate
    0.59
    áln
    0.56
    emun
    0.55
    лэ
    0.55
    inos
    0.54
    лма
    0.54
    inode
    0.54
    ines
    0.54
    Activations Density 0.004%

    No Known Activations