© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226998
    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_6_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
    м
    1.28
    ي
    1.12
    对
    1.03
    ни
    1.02
    zf
    1.02
    zetten
    1.02
    યર
    0.99
    osas
    0.98
     Elytres
    0.98
    t
    0.94
    POSITIVE LOGITS
    ↵↵
    1.16
    r
    1.07
    c
    0.89
    January
    0.87
    September
    0.86
    )`,
    0.86
    and
    0.84
     generational
    0.82
     logistical
    0.79
     safeguard
    0.78
    Activations Density 0.000%

    No Known Activations