© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200556
    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
     hard
    0.48
    难
    0.46
     difícil
    0.45
    hard
    0.43
     трудно
    0.43
     difficult
    0.42
    難
    0.42
    acent
    0.40
    Hard
    0.39
     difficile
    0.39
    POSITIVE LOGITS
    eniz
    0.38
    সিড
    0.38
     auraient
    0.37
     remarqué
    0.36
     ([[
    0.36
    ekw
    0.36
    ี้ยง
    0.36
    त्कार
    0.36
     myelin
    0.35
    ုပ်တို့
    0.35
    Activations Density 0.000%

    No Known Activations