© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201326
    Prev
    Next
    INDEX
    Explanations

    Common European Framework of Reference for Languages

    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_12_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
    ្យ
    0.25
    გი
    0.21
    鞍
    0.21
    ش
    0.19
    </h3>
    0.19
     Lionel
    0.19
     incentiv
    0.19
     الع
    0.18
     Lynch
    0.18
     कमाल
    0.18
    POSITIVE LOGITS
    java
    0.25
    >>
    0.22
    Correo
    0.22
    Т
    0.22
    ütte
    0.22
    il
    0.20
    øg
    0.20
    UN
    0.20
    Java
    0.20
    3
    0.20
    Activations Density 0.000%

    No Known Activations