© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90091
    Prev
    Next
    INDEX
    Explanations

    luggage, baggage, refugees, allowance

    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_11_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
    '
    0.19
    рії
    0.19
    웨어
    0.19
    화
    0.18
    करण
    0.18
    циа
    0.18
    ڈر
    0.17
    équilibre
    0.17
    சிவ
    0.17
     درجہ
    0.17
    POSITIVE LOGITS
     বলেছেন
    0.17
    xd
    0.17
    }-
    0.17
    .*;
    0.16
     lidí
    0.16
    0.16
     Welt
    0.16
     mensen
    0.16
     on
    0.15
    roy
    0.15
    Activations Density 0.001%

    No Known Activations