© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115754
    Prev
    Next
    INDEX
    Explanations

    levels: Low, Medium, High

    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_27_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
    COc
    0.37
     ECONOMIC
    0.34
     MENU
    0.34
    笠
    0.33
    次に
    0.33
    ፒ
    0.33
    쁠
    0.33
    ctu
    0.32
    ialis
    0.32
    だ
    0.32
    POSITIVE LOGITS
     eivät
    0.36
     iniziamo
    0.36
     painstaking
    0.34
     diğer
    0.34
     Verfügung
    0.34
    берём
    0.34
     अन्य
    0.33
     Oakland
    0.33
     painstakingly
    0.33
     इतर
    0.33
    Activations Density 0.026%

    No Known Activations