© 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. 159476
    Prev
    Next
    INDEX
    Explanations

    The Kooks

    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
     necesario
    1.11
     necessário
    1.10
     systèmes
    1.09
     nuove
    1.08
    :
    1.06
    ᱕
    1.05
     malicious
    1.04
    ﻓ
    1.03
     réaliser
    1.02
     profundo
    1.02
    POSITIVE LOGITS
    س
    1.91
    ن
    1.68
    f
    1.51
    с
    1.47
    st
    1.43
    s
    1.41
    re
    1.27
    si
    1.16
    स
    1.13
     They
    1.12
    Activations Density 0.000%

    No Known Activations