© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7089
    Prev
    Next
    INDEX
    Explanations

    internet addresses or references to blogs.

    oai_token-act-pair · gemini-2.0-flash

    website reference

    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
     bushels
    -0.40
     purpoſe
    -0.38
     ejus
    -0.33
     pleaſure
    -0.32
     Majefty
    -0.30
     craters
    -0.30
     ſtre
    -0.30
     miſ
    -0.30
     ſever
    -0.30
     quæ
    -0.30
    POSITIVE LOGITS
    
    0.73
    — 
    0.72
     تانيه
    0.70
    happens
    0.67
    bingo
    0.66
     >=",
    0.66
    colorful
    0.65
    principalColumn
    0.65
    throwaway
    0.65
    lovely
    0.65
    Activations Density 16.934%

    No Known Activations