© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3971
    Prev
    Next
    INDEX
    Explanations

    terms related to law and the constitution

    oai_token-act-pair · gemini-2.0-flash

    Words starting with "con/com/repre"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     piele
    -1.09
     acoper
    -1.08
     picioare
    -1.08
     argint
    -1.02
     maș
    -0.97
     prieten
    -0.94
     potrivit
    -0.91
     scurt
    -0.91
     noastre
    -0.90
     culoare
    -0.90
    POSITIVE LOGITS
     con
    1.15
     accom
    1.14
     com
    1.13
     destina
    1.06
     profes
    1.05
     investiga
    1.05
     combina
    1.05
     repre
    1.05
     partici
    1.04
     experi
    1.04
    Activations Density 13.306%

    No Known Activations