© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9451
    Prev
    Next
    INDEX
    Explanations

    C/C++ include statements using the '#' symbol

    oai_token-act-pair · gemini-2.0-flash

    #

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    :
    -0.47
     Beng
    -0.44
    ,
    -0.41
    ami
    -0.41
     ordinances
    -0.40
    (
    -0.40
    DataItem
    -0.39
     cameras
    -0.39
    .
    -0.39
    øren
    -0.38
    POSITIVE LOGITS
    OGND
    0.86
    Personendaten
    0.85
    VersionUID
    0.78
     '\\;'
    0.76
     насељу
    0.76
    ScopeManager
    0.76
    IsContent
    0.75
     дописавши
    0.74
    LookAnd
    0.74
    AddTagHelper
    0.74
    Activations Density 1.170%

    No Known Activations