© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144141
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    大
    0.54
    (^
    0.51
    న
    0.51
    ాన
    0.49
    जव
    0.49
    н
    0.48
    <unused2222>
    0.47
    一路
    0.47
    一对
    0.46
     nette
    0.46
    POSITIVE LOGITS
     収納
    0.64
     prace
    0.60
     メール
    0.60
     സര്‍ക്കാര്‍
    0.60
     spécial
    0.59
     pedibusque
    0.58
    이다
    0.57
     receptacles
    0.57
    nergie
    0.56
     tylko
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.