© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4144
    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_40_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
     ATTORNEY
    0.19
     ratione
    0.18
     PROTECTION
    0.18
     penjumlahan
    0.18
     destru
    0.18
    法則
    0.18
     COLUMN
    0.17
    緝
    0.17
    шение
    0.17
     danos
    0.17
    POSITIVE LOGITS
    K
    0.18
    -
    0.18
     F
    0.17
    L
    0.17
     S
    0.17
    se
    0.17
     emerged
    0.17
    F
    0.17
    S
    0.17
    Ts
    0.16
    Activations Density 0.000%

    No Known Activations