© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213592
    Prev
    Next
    INDEX
    Explanations

    complex curiosity

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    คับ
    0.37
    ≤
    0.36
    ynit
    0.35
    𝓬
    0.35
    чною
    0.35
     manifest
    0.34
     Milli
    0.34
    $-$,
    0.33
     manifesting
    0.33
    dolphin
    0.33
    POSITIVE LOGITS
     curious
    0.55
     queer
    0.54
     legacy
    0.52
     Curious
    0.49
     compound
    0.48
     curioso
    0.48
    legacy
    0.47
     Legacy
    0.46
     legacies
    0.45
     exposition
    0.45
    Activations Density 0.116%

    No Known Activations