© 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. 59323
    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
    ของ
    1.45
    ного
    1.24
    й
    1.20
     самих
    1.17
    िंग
    1.14
    ю
    1.14
    จะ
    1.13
    у
    1.13
    お
    1.12
     on
    1.11
    POSITIVE LOGITS
     for
    1.33
    -
    1.27
    em
    1.19
    F
    1.19
    0
    1.13
    i
    1.11
    n
    1.08
    ↵
    1.07
    <0x80>
    1.07
    el
    1.06
    Activations Density 0.000%

    No Known Activations