© 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. 1244
    Prev
    Next
    INDEX
    Explanations

    legal citations and other legal language

    oai_token-act-pair · 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
    ")));
    -0.64
    ientôt
    -0.64
     enfans
    -0.62
    ratulations
    -0.61
    disambiguation
    -0.61
    charcoal
    -0.61
    chassis
    -0.60
     dépens
    -0.60
    graduation
    -0.60
    smiles
    -0.60
    POSITIVE LOGITS
     Confucian
    0.38
     Negroes
    0.36
     Cæsar
    0.35
     Pues
    0.34
     Cantonese
    0.33
     Spearman
    0.33
     FZ
    0.33
     HUD
    0.32
     Aborig
    0.32
     Hopf
    0.32
    Activations Density 21.737%

    No Known Activations