© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211625
    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_5_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
    3
    1.17
     contenuto
    1.16
    ない
    1.12
     curator
    1.12
     presenceData
    1.07
     הז
    1.06
     crescita
    1.05
     повин
    1.04
     durumda
    1.04
     вули
    1.04
    POSITIVE LOGITS
    at
    1.86
    ad
    1.61
    d
    1.50
    y
    1.50
    as
    1.38
    م
    1.34
    h
    1.30
    <0x80>
    1.27
    f
    1.25
    b
    1.24
    Activations Density 0.000%

    No Known Activations