© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11605
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to collaborative technical support from manufacturers

    oai_token-act-pair · gemini-2.0-flash

    Foreign proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AndEndTag
    -0.82
     CreateTagHelper
    -0.76
    ValueStyle
    -0.70
    tagHelperRunner
    -0.69
    mybatisplus
    -0.61
    findpost
    -0.60
     beginnetje
    -0.59
    addGap
    -0.59
    contentLoaded
    -0.59
    انيف
    -0.57
    POSITIVE LOGITS
    QtWidgets
    0.48
     nasional
    0.47
     Nasional
    0.46
     UAB
    0.43
     ruch
    0.43
    JAKARTA
    0.43
    original
    0.43
     Reli
    0.42
     Uta
    0.42
     interesar
    0.42
    Activations Density 1.221%

    No Known Activations