© 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. 57917
    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
    of
    1.89
    ing
    1.33
    ier
    1.24
    m
    1.22
     of
    1.21
    over
    1.19
    up
    1.18
    en
    1.17
    ät
    1.15
    ový
    1.05
    POSITIVE LOGITS
    ж
    1.62
    ↵
    1.48
    ן
    1.34
    ש
    1.22
    ם
    1.20
    י
    1.17
    ა
    1.16
    다
    1.14
    τι
    1.13
    ی
    1.11
    Activations Density 0.000%

    No Known Activations