© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56361
    Prev
    Next
    INDEX
    Explanations

    that followed by way or can

    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_11_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
    ल
    0.61
    nto
    0.58
    thers
    0.58
     कर
    0.56
    aundry
    0.56
    bst
    0.55
    ęp
    0.55
    ollen
    0.55
    barrow
    0.55
    ndez
    0.55
    POSITIVE LOGITS
    म
    0.77
    he
    0.76
    on
    0.74
    מ
    0.71
    am
    0.66
     was
    0.64
    s
    0.61
     which
    0.59
    তারপর
    0.59
    ম
    0.59
    Activations Density 0.026%

    No Known Activations