© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10899
    Prev
    Next
    INDEX
    Explanations

    text featuring blogs and awards

    oai_token-act-pair · gemini-2.0-flash

    words related to features or categories

    np_token-act-pair-logits · gpt-4o-mini

    feature

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DeleteBehavior
    -0.71
     AssemblyCulture
    -0.69
    EndGlobalSection
    -0.65
     NgModule
    -0.63
    yakarta
    -0.62
    zos
    -0.60
    LookAnd
    -0.59
     صوتيه
    -0.59
     Мексичка
    -0.58
    Expedia
    -0.58
    POSITIVE LOGITS
    Feature
    0.65
     Features
    0.57
     Feature
    0.56
    WireFormatLite
    0.55
     Down
    0.54
     columnas
    0.53
     feature
    0.53
    Down
    0.53
     features
    0.53
     columna
    0.50
    Activations Density 2.185%

    No Known Activations