© 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. 120280
    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
     superposition
    0.39
     مض
    0.37
    𝒶
    0.36
     frecuencia
    0.36
    ému
    0.36
     আর্ম
    0.35
    plotlib
    0.35
    ANIUM
    0.35
     velocidad
    0.35
     철
    0.35
    POSITIVE LOGITS
    जागरण
    0.42
    ooky
    0.40
     sightings
    0.40
    来源
    0.39
     शुक्
    0.38
    锵
    0.38
    resher
    0.38
     downtown
    0.38
     dishwasher
    0.38
    嗷
    0.37
    Activations Density 0.000%

    No Known Activations