© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35273
    Prev
    Next
    INDEX
    Explanations

    supplementary, complementary

    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_3_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
    sha
    0.64
    مون
    0.64
    sk
    0.64
     for
    0.63
    ung
    0.63
    í
    0.63
    icht
    0.59
    ]
    0.58
    á
    0.58
    ik
    0.57
    POSITIVE LOGITS
    י
    0.89
    ר
    0.83
     complementar
    0.78
    ي
    0.77
    ра
    0.76
    ول
    0.71
    <0xA1>
    0.70
    る
    0.70
     complément
    0.68
     complements
    0.68
    Activations Density 0.012%

    No Known Activations