© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159583
    Prev
    Next
    INDEX
    Explanations

    fawqa, Taghut

    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_2_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
     quá
    1.43
    ﻨ
    1.20
     documenti
    1.18
     không
    1.17
     linii
    1.16
    ước
    1.14
     destek
    1.14
     tessuto
    1.14
     puesto
    1.13
     drugih
    1.13
    POSITIVE LOGITS
    f
    1.39
    t
    1.38
    l
    1.24
    c
    1.23
    p
    1.23
    ↵↵
    1.18
    b
    1.16
    pel
    1.16
    am
    1.15
    lere
    1.15
    Activations Density 0.001%

    No Known Activations