© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108957
    Prev
    Next
    INDEX
    Explanations

    EGR Cooler or Valve

    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_2_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
     contrôle
    1.09
    in
    1.07
     for
    1.00
    երը
    0.98
    u
    0.98
     la
    0.97
     have
    0.97
    的
    0.95
    ing
    0.93
     be
    0.91
    POSITIVE LOGITS
    ж
    1.38
    м
    1.22
    ц
    1.18
    .
    1.11
    т
    1.11
    on
    1.09
    ן
    1.02
    x
    0.96
    на
    0.96
    ل
    0.96
    Activations Density 0.000%

    No Known Activations