© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135681
    Prev
    Next
    INDEX
    Explanations

    to give you the *best*

    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_37_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
     가장
    0.74
     सबसे
    0.73
    最
    0.72
     સૌથી
    0.71
    ที่สุด
    0.70
     সবচেয়ে
    0.69
     सर्वात
    0.69
     সবচেয়ে
    0.68
     найбільш
    0.66
    的最
    0.64
    POSITIVE LOGITS
     دادن
    0.35
     ilişkin
    0.34
     samb
    0.34
    饺
    0.34
    必要な
    0.33
     perch
    0.33
    istle
    0.32
    easing
    0.32
    łe
    0.32
    ={`${
    0.32
    Activations Density 0.009%

    No Known Activations