© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2224
    Prev
    Next
    INDEX
    Explanations

    pressure and power differences

    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_40_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
    ние
    0.40
    )]);
    0.38
    peek
    0.38
     kennt
    0.36
    "]));
    0.35
    gebung
    0.35
    ब्र
    0.34
     odb
    0.33
     widers
    0.33
    utzer
    0.33
    POSITIVE LOGITS
     difference
    1.98
     Difference
    1.84
    Difference
    1.77
    差
    1.77
    difference
    1.73
     diferença
    1.72
     différence
    1.65
     differenza
    1.60
     differences
    1.58
     diferencia
    1.55
    Activations Density 0.163%

    No Known Activations