© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131526
    Prev
    Next
    INDEX
    Explanations

    Arxiv followed by paper type

    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
    "
    0.84
    、
    0.84
    ни
    0.83
     تحقيق
    0.80
    ح
    0.80
    ،
    0.78
    、“
    0.76
     لكن
    0.75
    AAP
    0.74
     يش
    0.74
    POSITIVE LOGITS
     I
    1.10
     ancienne
    1.01
     agak
    0.97
     umana
    0.97
    ید
    0.95
     immunoblot
    0.94
     aging
    0.92
     aerospace
    0.92
     of
    0.91
     appliqué
    0.89
    Activations Density 0.000%

    No Known Activations