© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 64193
    Prev
    Next
    INDEX
    Explanations

    direct, found

    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_59_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
     devenue
    0.39
     tr
    0.38
     become
    0.37
    划
    0.37
     becoming
    0.37
    放在
    0.37
     fund
    0.36
    தை
    0.36
    fund
    0.36
    S
    0.36
    POSITIVE LOGITS
     direct
    0.82
     Direct
    0.81
     found
    0.80
    direct
    0.79
    found
    0.76
     Found
    0.75
    Direct
    0.73
    Found
    0.71
     diretta
    0.65
     time
    0.64
    Activations Density 0.006%

    No Known Activations