© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211673
    Prev
    Next
    INDEX
    Explanations

    TNM staging, classifications, 5, zero

    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_5_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
     an
    1.63
    {
    1.55
     can
    1.34
     be
    1.27
    a
    1.27
    _
    1.27
    ك
    1.20
    ING
    1.16
    י
    1.12
    AR
    1.09
    POSITIVE LOGITS
    r
    1.31
    <0x0D>
    1.28
    بود
    1.08
    να
    1.06
    rins
    0.94
    lty
    0.94
    u
    0.93
    ong
    0.93
    lig
    0.91
    itabbam
    0.90
    Activations Density 0.000%

    No Known Activations