© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 151365
    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_23_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
     indenture
    0.55
    ﻊ
    0.55
    umetric
    0.52
     deductive
    0.51
     commemorative
    0.50
    etic
    0.48
     preservation
    0.48
     receiver
    0.48
     asbestos
    0.47
    Р
    0.47
    POSITIVE LOGITS
    お
    0.52
    ホ
    0.51
    Ste
    0.49
    ネ
    0.46
    Gra
    0.45
     kraja
    0.44
    Fif
    0.44
     powiedział
    0.44
    ヴェ
    0.43
     stanu
    0.43
    Activations Density 0.000%

    No Known Activations