© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7565
    Prev
    Next
    INDEX
    Explanations

    words related to electronic devices, particularly the Kindle and Galaxy Tab

    oai_token-act-pair · gemini-2.0-flash

    technology and gadget reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    tagHelperRunner
    -0.78
     חיצוניים
    -0.61
     initComponents
    -0.60
     beginnetje
    -0.56
    Krok
    -0.56
    Portály
    -0.52
    Personensuche
    -0.52
    obes
    -0.52
     bağlantılar
    -0.49
    舺
    -0.49
    POSITIVE LOGITS
    TagHelper
    0.59
    cshtml
    0.58
     createState
    0.58
    @[+][
    0.56
     Sleeve
    0.50
     CarPlay
    0.48
     JNI
    0.46
    +:+
    0.45
     Nvidia
    0.45
    AxisAlignment
    0.45
    Activations Density 10.532%

    No Known Activations