© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16139
    Prev
    Next
    INDEX
    Explanations

    questions where someone is seeking help to understand an issue

    oai_token-act-pair · gemini-2.0-flash

    am

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Pozri
    -0.52
     themselves
    -0.50
    Pranala
    -0.48
     AttributeSet
    -0.47
     AspNetCore
    -0.47
    iecie
    -0.46
     confronti
    -0.44
     Maladies
    -0.43
    /*
    -0.43
    вето
    -0.43
    POSITIVE LOGITS
     am
    3.30
    Am
    2.53
     Am
    2.52
    am
    2.13
     AM
    1.90
    AM
    1.62
     Amm
    1.38
    amm
    1.29
    Amm
    1.24
     ам
    1.23
    Activations Density 1.840%

    No Known Activations