© 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. 12947
    Prev
    Next
    INDEX
    Explanations

    the word "map" in the context of computer science

    oai_token-act-pair · gemini-2.0-flash

    Map

    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
    Schedulers
    -0.65
    podar
    -0.55
    jarah
    -0.53
     getLogin
    -0.52
    คาร
    -0.49
    vodní
    -0.49
    playable
    -0.49
    IsPostBack
    -0.48
     handelt
    -0.48
    clause
    -0.48
    POSITIVE LOGITS
    AutoScaleMode
    0.72
    TintMode
    0.68
    RTEE
    0.62
    fillType
    0.61
     pinulongan
    0.59
    Brainz
    0.56
    styleType
    0.56
     استنادى
    0.55
     otomatig
    0.54
    ModelAdmin
    0.53
    Activations Density 1.766%

    No Known Activations