© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212807
    Prev
    Next
    INDEX
    Explanations

    -ine compounds

    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_5_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
    ని
    1.38
    ی
    1.30
    یی
    1.06
    ン
    1.03
    segaretro
    0.98
    ים
    0.97
    นะ
    0.97
     ﺍﻟ
    0.94
    いません
    0.93
    ۸
    0.93
    POSITIVE LOGITS
    st
    1.22
    is
    1.18
    ter
    1.16
    of
    1.14
    ade
    1.13
    it
    1.11
    ur
    1.11
    at
    1.09
    le
    1.08
    c
    1.04
    Activations Density 0.001%

    No Known Activations