© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65184
    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
    宪
    0.48
    憲
    0.44
    前者
    0.43
    邃
    0.42
    𝐜
    0.40
    ARRIVAL
    0.40
    фици
    0.40
     कक्क
    0.40
     குண
    0.40
    origData
    0.39
    POSITIVE LOGITS
     Companion
    0.41
    栖
    0.37
     élet
    0.36
     companion
    0.35
    ili
    0.35
     keyed
    0.35
    Companion
    0.35
     fat
    0.34
    enk
    0.34
     express
    0.34
    Activations Density 0.000%

    No Known Activations