© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227706
    Prev
    Next
    INDEX
    Explanations

    Doge's Palace or court

    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
     oligonucleotide
    0.94
    اء
    0.93
    ה
    0.91
    る
    0.88
    dır
    0.86
     cellule
    0.86
    dı
    0.85
    هما
    0.84
    고
    0.83
     generalization
    0.82
    POSITIVE LOGITS
    r
    1.08
    th
    1.01
    2
    0.98
    sp
    0.96
    ist
    0.96
    gh
    0.94
    im
    0.87
    pot
    0.84
    w
    0.84
    am
    0.82
    Activations Density 0.000%

    No Known Activations