© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151746
    Prev
    Next
    INDEX
    Explanations

    display DataFrame

    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_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    地
    0.52
     HOLDERS
    0.47
     innych
    0.47
     borderWidth
    0.46
     miembros
    0.45
     चौकी
    0.45
     pihak
    0.45
    iko
    0.44
    াদির
    0.44
    <0x97>
    0.44
    POSITIVE LOGITS
     absc
    0.47
     elegantes
    0.46
    plic
    0.46
     nasce
    0.46
    να
    0.45
    рея
    0.45
     faça
    0.44
    하세요
    0.43
    Segoe
    0.43
    Punk
    0.43
    Activations Density 0.001%

    No Known Activations