© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81478
    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_29_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
     водой
    0.40
    ]$,
    0.37
    ଣ୍
    0.35
    灣
    0.34
     பெய
    0.34
     হিন্দ
    0.34
     actuated
    0.33
    vykor
    0.33
    喎
    0.33
     peric
    0.32
    POSITIVE LOGITS
    tugraz
    0.40
     selfishness
    0.38
     selfish
    0.38
     sort
    0.37
     inept
    0.37
     superintend
    0.37
    alez
    0.37
    აშ
    0.35
     equally
    0.35
     neglect
    0.35
    Activations Density 0.000%

    No Known Activations