© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211917
    Prev
    Next
    INDEX
    Explanations

    Huxley,abre,macabre

    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_5_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
    is
    1.54
    ми
    1.27
    ли
    1.25
    는
    1.20
    х
    1.18
    ید
    1.09
    их
    1.05
    но
    1.04
    rotechn
    1.03
    getBean
    1.02
    POSITIVE LOGITS
    ك
    1.19
    ס
    1.08
     to
    1.05
     protege
    1.00
    ל
    1.00
     nucl
    0.99
    ]
    0.99
    ل
    0.98
     Gerade
    0.97
    ד
    0.97
    Activations Density 0.000%

    No Known Activations