© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214566
    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_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
    t
    1.84
    s
    1.36
    to
    1.19
    ture
    1.09
    de
    1.06
    truck
    1.06
    𝐭
    1.06
    the
    1.05
    ten
    1.05
    dL
    1.05
    POSITIVE LOGITS
    ک
    1.23
     αλλά
    1.15
    شک
    1.13
     sitä
    1.09
    کول
    1.09
     industria
    1.07
    Ӣ
    1.07
    Ե
    1.05
     dû
    1.04
     راجسټ
    1.04
    Activations Density 0.001%

    No Known Activations