© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203035
    Prev
    Next
    INDEX
    Explanations

    outsiders, outsourcing

    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_6_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
    0
    1.07
     to
    1.03
    u
    0.96
    are
    0.96
     {
    0.95
    ার
    0.93
    and
    0.93
     and
    0.88
    ator
    0.88
    </h2>
    0.86
    POSITIVE LOGITS
    c
    0.98
    vær
    0.93
    کرا
    0.87
    zī
    0.86
    kelijk
    0.86
    禕
    0.84
    v
    0.83
    डी
    0.83
    इये
    0.83
    ký
    0.82
    Activations Density 0.000%

    No Known Activations