© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167788
    Prev
    Next
    INDEX
    Explanations

    Literature concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     //
    0.41
    ׃
    0.40
     /
    0.36
    Neu
    0.35
    ُل
    0.35
    )/
    0.34
    mvn
    0.34
    ↵
    0.34
    <tr>
    0.34
     Couch
    0.34
    POSITIVE LOGITS
     কা
    0.38
     registrazione
    0.37
    的原
    0.37
     كا
    0.36
     multimedia
    0.35
     filesystem
    0.35
    يديو
    0.34
    ดิน
    0.34
     മൊ
    0.34
     ca
    0.34
    Activations Density 0.003%

    No Known Activations