© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228109
    Prev
    Next
    INDEX
    Explanations

    Sheets("SheetName")

    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_6_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
     are
    1.16
     in
    1.07
     $
    1.02
     can
    1.02
     è
    1.02
     =
    0.96
     '
    0.92
    ิ
    0.90
    ];
    0.89
    f
    0.87
    POSITIVE LOGITS
    он
    1.05
     saludables
    0.98
     personales
    0.98
    enciais
    0.98
    ắc
    0.93
     acht
    0.93
    aza
    0.92
    <unused2213>
    0.92
     élevés
    0.91
    olds
    0.91
    Activations Density 0.004%

    No Known Activations