© 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. 14076
    Prev
    Next
    INDEX
    Explanations

    words that are technical terms related to specific types of equipment or tools

    oai_token-act-pair · 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
    Ход
    -0.46
     okuyayım
    -0.46
     gawas
    -0.43
     intptr
    -0.42
     &___
    -0.42
    providedIn
    -0.42
     kasarigan
    -0.41
     SwitchCompat
    -0.41
    FTFY
    -0.40
    Jeografia
    -0.38
    POSITIVE LOGITS
    #+#
    0.64
    NOPQRST
    0.64
    NgModule
    0.62
    MENAFN
    0.61
    KommentareTeilen
    0.61
     CreateTagHelper
    0.60
    rinfo
    0.57
     jadx
    0.55
     strdup
    0.54
    tagHelperRunner
    0.53
    Activations Density 7.041%

    No Known Activations