© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117537
    Prev
    Next
    INDEX
    Explanations

    contrastive, deep learning, retention, open source, collective fraud, exploration, causality, latent embeddings

    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
     दशकों
    0.36
    ﻘ
    0.35
     অথবা
    0.35
    蔬菜
    0.34
     edible
    0.33
     edibles
    0.33
     و
    0.33
     الخ
    0.33
    دع
    0.32
     এবং
    0.32
    POSITIVE LOGITS
    (*)
    0.34
    ellig
    0.30
    ₍
    0.30
     подчи
    0.29
    AxisAlignment
    0.28
    ⁽
    0.27
    [:
    0.27
    magenta
    0.27
    ขาว
    0.27
     Lobkowicz
    0.27
    Activations Density 0.007%

    No Known Activations