© 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. 3501
    Prev
    Next
    INDEX
    Explanations

    publication information, especially including names, places, and dates

    oai_token-act-pair · gemini-2.0-flash

    citations

    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
    mybatisplus
    -0.80
    BagConstraints
    -0.65
    kháu
    -0.63
    berdayakan
    -0.60
     sportiva
    -0.57
    InSection
    -0.55
    Espèce
    -0.54
    BindingResult
    -0.54
    gameserver
    -0.53
     fernández
    -0.52
    POSITIVE LOGITS
     noDo
    0.66
     CreateTagHelper
    0.57
     LaSalle
    0.54
    帖最后由
    0.54
    windig
    0.54
     Garden
    0.50
    beb
    0.50
    matchCondition
    0.49
     lan
    0.49
     Lan
    0.48
    Activations Density 0.605%

    No Known Activations