© 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. 4623
    Prev
    Next
    INDEX
    Explanations

    terms associated with software programming and compilation

    oai_token-act-pair · gemini-2.0-flash

    definition

    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
     snippetHide
    -0.65
    migrationBuilder
    -0.59
    Datuak
    -0.57
     spic
    -0.56
    ništvo
    -0.54
     ">=
    -0.52
    esModule
    -0.51
     utafitiHapana
    -0.50
    WriteTagHelper
    -0.50
    لينكات
    -0.50
    POSITIVE LOGITS
     definition
    1.75
     definitions
    1.54
    definition
    1.42
     Definition
    1.41
    Definition
    1.32
     définition
    1.31
     term
    1.26
     DEFINITION
    1.23
    definitions
    1.23
    DEFINITION
    1.21
    Activations Density 5.294%

    No Known Activations