© 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. 61228
    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
    om
    1.51
    غ
    1.36
    ing
    1.34
    den
    1.26
    ח
    1.25
    \
    1.20
    人
    1.18
    dem
    1.16
    ete
    1.16
    h
    1.14
    POSITIVE LOGITS
     launched
    1.09
     name
    1.06
     grassy
    1.06
     weathered
    1.05
    ות
    1.04
    те
    1.03
     borrowed
    1.02
     kullanıl
    1.02
     marred
    1.02
     radiated
    1.01
    Activations Density 0.000%

    No Known Activations