© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13426
    Prev
    Next
    INDEX
    Explanations

    named entities and the words around them

    oai_token-act-pair · gemini-2.0-flash

    text with irregular or non-English characters

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

    foreign words/code

    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
    zzlies
    -0.73
     CURIAM
    -0.61
    nals
    -0.60
    ”،
    -0.60
     Đường
    -0.60
    هرست
    -0.59
    //</
    -0.59
    URDAY
    -0.58
    NESDAY
    -0.58
    ÓS
    -0.57
    POSITIVE LOGITS
     متعلقه
    0.85
     فريبيس
    0.57
    $_['
    0.54
    duğu
    0.51
    UserScript
    0.50
    InjectAttribute
    0.49
     '{@
    0.48
    farwyddwr
    0.47
    PathParam
    0.46
     volon
    0.45
    Activations Density 1.900%

    No Known Activations