© 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. 9689
    Prev
    Next
    INDEX
    Explanations

    instances of something being found or found out

    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
     find
    -2.72
    find
    -2.63
     finds
    -2.59
     finding
    -2.53
     FIND
    -2.47
    Find
    -2.45
     Find
    -2.45
    finding
    -2.39
    FIND
    -2.38
     Finding
    -2.36
    POSITIVE LOGITS
    SOUNDBITE
    0.48
    Thunk
    0.45
    EClass
    0.45
     Вікі
    0.44
    ursales
    0.40
     Bellini
    0.39
    ومة
    0.39
    chitis
    0.38
    ça
    0.38
    DT
    0.38
    Activations Density 3.679%

    No Known Activations