© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200703
    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_46_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
     ब्ल
    0.39
    벵
    0.39
     בל
    0.39
     arcu
    0.38
     폭
    0.37
    လို့
    0.37
    ZV
    0.37
     Arundel
    0.36
    Lion
    0.36
     có
    0.36
    POSITIVE LOGITS
     низ
    0.50
    低
    0.44
     low
    0.43
    low
    0.42
    min
    0.39
    저
    0.39
     低
    0.38
     ratios
    0.38
     min
    0.38
    Marshal
    0.37
    Activations Density 0.000%

    No Known Activations