© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159622
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    1
    1.52
    s
    1.31
    ET
    1.09
    OD
    1.07
    OT
    1.05
    č
    1.03
    AIN
    1.00
    webm
    0.99
    AVE
    0.97
    㶲
    0.97
    POSITIVE LOGITS
    ли
    1.58
    ו
    1.27
    ،
    1.23
     appendices
    1.20
    ب
    1.20
    ۔
    1.17
    ק
    1.16
    ू
    1.12
     an
    1.11
    л
    1.09
    Activations Density 0.000%

    No Known Activations