© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44547
    Prev
    Next
    INDEX
    Explanations

    government or operational

    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_13_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
    s
    0.78
    1
    0.50
    }
    0.50
    <h2>
    0.47
    ional
    0.46
    -----
    0.46
    ----
    0.45
    2
    0.44
    3
    0.44
    <h4>
    0.44
    POSITIVE LOGITS
    (['
    0.54
    ствующие
    0.49
    კი
    0.48
     luckily
    0.48
    стви
    0.47
    という
    0.47
    ುತ್ತಿದ್ದ
    0.46
    ϑ
    0.46
     ಔಷಧ
    0.46
     banished
    0.46
    Activations Density 0.000%

    No Known Activations