© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130541
    Prev
    Next
    INDEX
    Explanations

    addressing issues and challenges

    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_1_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
    ↵↵
    1.36
    ara
    1.23
    ler
    1.11
    um
    1.10
    es
    1.09
    les
    1.08
    ab
    1.06
    un
    1.05
    ani
    1.04
    ung
    1.03
    POSITIVE LOGITS
    ﻟ
    1.10
     tabela
    1.09
    ᱒
    1.08
     svim
    1.05
     зміню
    1.05
     gdy
    1.02
     linii
    1.02
     magie
    1.02
    ﺝ
    1.02
     joue
    1.01
    Activations Density 0.000%

    No Known Activations