© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107443
    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
    ↵
    1.58
    ك
    1.48
    ى
    1.34
    к
    1.27
    de
    1.26
    ض
    1.19
    ка
    1.18
    ته
    1.14
    ات
    1.06
    و
    0.98
    POSITIVE LOGITS
    りと
    1.34
     renormal
    1.18
     novi
    1.10
     carreras
    1.09
     liczb
    1.09
     membrana
    1.08
     וא
    1.07
     mnogo
    1.07
     reforzar
    1.07
     permanec
    1.06
    Activations Density 0.000%

    No Known Activations