© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21323
    Prev
    Next
    INDEX
    Explanations

    latte

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    msch
    0.36
    ahami
    0.36
    ксана
    0.35
    rVert
    0.35
    డ
    0.34
    \;\
    0.34
    தை
    0.34
     संयोजक
    0.34
    iophorus
    0.34
    🔷
    0.33
    POSITIVE LOGITS
     lat
    1.68
     latt
    1.48
     LAT
    1.45
     ল
    1.41
     latte
    1.38
     ल
    1.36
    Lat
    1.34
    l
    1.33
    latt
    1.28
     Lat
    1.27
    Activations Density 0.096%

    No Known Activations