© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257176
    Prev
    Next
    INDEX
    Explanations

    to recipients and callable bonds

    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_22_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
    렬
    0.50
    ˘
    0.48
     首先
    0.46
    蜼
    0.46
    ائه
    0.45
     spolu
    0.45
    ﺕ
    0.45
     retten
    0.44
     istraž
    0.44
     centenary
    0.44
    POSITIVE LOGITS
    шли
    0.44
    -
    0.42
    co
    0.41
    Diffusion
    0.40
    homeini
    0.39
    Education
    0.39
     سبب
    0.39
    "،
    0.38
     Diffusion
    0.38
    istungs
    0.38
    Activations Density 0.000%

    No Known Activations