© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5116
    Prev
    Next
    INDEX
    Explanations

    people's names

    oai_token-act-pair · gemini-2.0-flash

    Dialogue

    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
    Rptr
    -0.56
    enterOuterAlt
    -0.56
    Whew
    -0.49
    IGraphics
    -0.47
    Награды
    -0.44
    openzeppelin
    -0.43
    äv
    -0.42
     fix
    -0.41
     sockaddr
    -0.40
    setupUi
    -0.40
    POSITIVE LOGITS
     lenker
    0.76
     externi
    0.68
     estimés
    0.63
     Савезне
    0.61
     autorytatywna
    0.61
    Билгалдахарш
    0.61
     CreateTagHelper
    0.60
    intios
    0.59
    webElementGuid
    0.58
    optString
    0.58
    Activations Density 1.084%

    No Known Activations