© 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. 6841
    Prev
    Next
    INDEX
    Explanations

    dimensions or prices

    oai_token-act-pair · gemini-2.0-flash

    formatted dimensions and prices

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

    x

    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
    SequentialGroup
    -0.86
    IUrlHelper
    -0.84
    addCriterion
    -0.84
     Exactos
    -0.81
    complexContent
    -0.78
    MessageOf
    -0.74
    InitVars
    -0.73
    ۜ
    -0.69
    HasAnnotation
    -0.69
    webElementXpaths
    -0.69
    POSITIVE LOGITS
     itſelf
    0.53
    NUMX
    0.48
     raiſ
    0.47
     deſt
    0.47
     myſelf
    0.46
    leſs
    0.41
     quæ
    0.41
     ſta
    0.38
     difp
    0.38
    pack
    0.37
    Activations Density 4.852%

    No Known Activations