© 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. 110088
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1
    1.66
    ان
    1.48
    .
    1.47
    an
    1.40
    its
    1.32
    to
    1.25
    sh
    1.22
    I
    1.17
    way
    1.16
    0
    1.16
    POSITIVE LOGITS
    €™
    1.20
    ﻪ
    1.13
     dupa
    1.05
     ও
    1.03
    ので
    1.03
    ﺒ
    1.00
     avut
    0.99
    ায
    0.98
    ა
    0.98
     ফলে
    0.97
    Activations Density 0.000%

    No Known Activations