© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202519
    Prev
    Next
    INDEX
    Explanations

    Johnson Space Center audience

    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
     p
    0.50
    OOSE
    0.48
     przyp
    0.47
    TION
    0.47
    ောက်ပ
    0.47
     nasi
    0.45
     bali
    0.45
    konstru
    0.45
    aviti
    0.45
    ｓ
    0.45
    POSITIVE LOGITS
    ябре
    0.57
     Sociales
    0.53
     years
    0.52
     Некоторые
    0.52
     विश्व
    0.51
     Lewis
    0.51
     През
    0.50
    笘
    0.50
     Luego
    0.49
     ඔවුන්
    0.49
    Activations Density 0.000%

    No Known Activations