© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199500
    Prev
    Next
    INDEX
    Explanations

    greetings

    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_46_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
    ियत
    0.50
     প্রক
    0.39
    ye
    0.38
     ü
    0.38
    yo
    0.38
    yeh
    0.37
     Tak
    0.36
    ިޔ
    0.36
     नजर
    0.36
    yu
    0.36
    POSITIVE LOGITS
    連続
    0.38
    emission
    0.38
    ruled
    0.37
    पीठ
    0.36
    तिहासिक
    0.36
     pemain
    0.36
     მშ
    0.36
     মৌ
    0.34
    魯
    0.34
     өл
    0.34
    Activations Density 0.009%

    No Known Activations