© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36028
    Prev
    Next
    INDEX
    Explanations

    code structure and symbols

    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_31_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
    चुअल
    0.39
    ERE
    0.39
    TITLE
    0.38
     ઓ
    0.38
    Spice
    0.38
    ঘ্রই
    0.37
     Laut
    0.37
    ARIO
    0.37
     Desarrollo
    0.36
    Brandon
    0.36
    POSITIVE LOGITS
     allied
    0.41
     brim
    0.40
     பாட
    0.38
     conting
    0.37
     त्यानुसार
    0.36
     primed
    0.35
    იდან
    0.35
     mediated
    0.35
    </thead>
    0.35
     idi
    0.35
    Activations Density 0.116%

    No Known Activations