© 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. 36304
    Prev
    Next
    INDEX
    Explanations

    "Black Box" Problem

    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
    <0x0D>
    0.63
    ?
    0.59
    ק
    0.58
    к
    0.54
    м
    0.50
    </h4>
    0.50
    ্ল
    0.48
    ц
    0.48
    л
    0.46
    д
    0.46
    POSITIVE LOGITS
     നെറ്റ്‌വർ
    0.57
     Ka
    0.51
     nebude
    0.51
     royal
    0.49
     POV
    0.47
    পালা
    0.47
     Without
    0.47
     deploying
    0.46
     הו
    0.46
     애니
    0.45
    Activations Density 0.001%

    No Known Activations