© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44399
    Prev
    Next
    INDEX
    Explanations

    safe haven asset

    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_13_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
     concordance
    0.56
     mumbai
    0.56
     NYC
    0.55
     friday
    0.54
     punk
    0.53
     TCE
    0.52
    ᕆ
    0.51
     viernes
    0.50
     bactéries
    0.50
    瑷
    0.50
    POSITIVE LOGITS
    стное
    0.51
    ita
    0.50
    ፈር
    0.48
     ม
    0.48
     والمت
    0.48
     المقسوم
    0.48
    Loy
    0.48
    ")),
    0.47
     Ship
    0.47
    ย
    0.47
    Activations Density 0.000%

    No Known Activations