© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12696
    Prev
    Next
    INDEX
    Explanations

    the programming keyword "int" and the variable "i" used in loops

    oai_token-act-pair · gemini-2.0-flash

    int

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    SuccessListener
    -0.63
    #
    -0.59
    complexContent
    -0.59
    úgó
    -0.57
    altezza
    -0.57
    ValueStyle
    -0.56
    galus
    -0.55
     JpaRepository
    -0.54
    ennis
    -0.53
    ètre
    -0.52
    POSITIVE LOGITS
    principalColumn
    0.79
     protoimpl
    0.57
    TagHelper
    0.57
    abilia
    0.57
    onActivityResult
    0.54
     gyhoeddwyd
    0.51
    skjaer
    0.48
    BrowserModule
    0.48
     AssemblyCompany
    0.46
     liable
    0.45
    Activations Density 0.113%

    No Known Activations