© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198703
    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_27_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
    textSize
    0.45
     euthan
    0.40
     wherein
    0.40
    ლე
    0.39
     netted
    0.39
     অয়েল
    0.39
    ulfite
    0.39
    Ꮬ
    0.39
    ▿
    0.39
     saute
    0.39
    POSITIVE LOGITS
    Child
    0.42
    Lic
    0.37
    IDS
    0.37
     சில
    0.37
     клини
    0.36
     pakk
    0.36
    Schema
    0.36
     rinnov
    0.36
    几
    0.36
     управ
    0.35
    Activations Density 0.000%

    No Known Activations