© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1212
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    cgColor
    1.41
    lar
    1.26
    া
    1.25
    ル
    1.22
    a
    1.20
    modifiers
    1.16
    light
    1.14
    𝕣
    1.12
    સ
    1.11
    ri
    1.09
    POSITIVE LOGITS
     penchant
    1.27
    
    1.23
    
    1.23
    ﺗ
    1.18
    ingly
    1.16
     DQN
    1.16
     powerhouse
    1.15
     supporting
    1.13
    놈
    1.12
     lovers
    1.11
    Activations Density 0.020%

    No Known Activations