© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219478
    Prev
    Next
    INDEX
    Explanations

    computable, solvable, capacitor

    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_31_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
    襖
    0.43
    埔
    0.43
     उद्देश्य
    0.41
     করিয়৷
    0.39
    Kenn
    0.39
    ಂಜ
    0.39
    নিজের
    0.39
    Რ
    0.38
    𝐑
    0.38
     பெற
    0.38
    POSITIVE LOGITS
     computable
    0.42
     solvable
    0.41
     Dét
    0.39
     OLED
    0.38
     Bid
    0.37
    시다
    0.37
     capac
    0.36
     explic
    0.36
     छे
    0.36
    ้ว
    0.36
    Activations Density 0.000%

    No Known Activations