© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164124
    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_13_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
    ្ន
    0.50
     Alfvén
    0.47
     Ruta
    0.47
     صدا
    0.46
     époque
    0.45
     वस्तू
    0.44
    স
    0.44
     Então
    0.44
     Aeronaut
    0.44
     FIELDS
    0.44
    POSITIVE LOGITS
    ziest
    0.48
    Else
    0.46
    তিকর
    0.45
    及
    0.44
    坳
    0.44
    t
    0.44
    M
    0.43
    Buildable
    0.43
    长安
    0.42
    impul
    0.42
    Activations Density 0.000%

    No Known Activations