© 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. 89620
    Prev
    Next
    INDEX
    Explanations

    fighting continues intensely

    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
     hechos
    0.54
     adenine
    0.52
     Luz
    0.51
     تي
    0.51
     ク
    0.50
     fotografías
    0.50
    grö
    0.49
     Raza
    0.49
     سری
    0.48
     Mera
    0.48
    POSITIVE LOGITS
    È
    0.56
    Έ
    0.52
    ടതി
    0.51
    Answer
    0.49
    Ë
    0.49
    ज़
    0.49
    ፂ
    0.48
    <h3>
    0.47
     to
    0.47
     counterbalance
    0.47
    Activations Density 0.000%

    No Known Activations