© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7067
    Prev
    Next
    INDEX
    Explanations

    words having to do with city planning and urban areas and uses of space

    oai_token-act-pair · gemini-2.0-flash

    locations and directions

    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
    SourceChecksum
    -0.84
     arşivlendi
    -0.68
     protoimpl
    -0.68
    expandindo
    -0.65
    ViewFeatures
    -0.62
    CompilerServices
    -0.61
    ContentAsync
    -0.61
    LabelTagHelper
    -0.59
    parsedMessage
    -0.59
    SizeMode
    -0.59
    POSITIVE LOGITS
    uario
    0.47
    arah
    0.42
    cjach
    0.41
    InputChange
    0.41
    kuti
    0.41
    SystemColors
    0.40
     eingesch
    0.40
    lofen
    0.40
    : 
    0.38
     BoxFit
    0.38
    Activations Density 1.212%

    No Known Activations