© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194410
    Prev
    Next
    INDEX
    Explanations

    sum of subarrays

    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_27_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
    欲
    0.40
    ออกจาก
    0.34
    StatusInternal
    0.34
     সাক্ষাৎকার
    0.34
    আমি
    0.32
    ങ്ങളെ
    0.32
     Wissenschaften
    0.32
    "/>
    0.32
     kisses
    0.32
    場合に
    0.32
    POSITIVE LOGITS
    ﻈ
    0.44
    asilkan
    0.42
     quartet
    0.42
     Ks
    0.41
     deten
    0.40
     rutin
    0.40
     multinationals
    0.40
     shouted
    0.39
     amort
    0.39
     verticals
    0.39
    Activations Density 0.000%

    No Known Activations