© 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. 12591
    Prev
    Next
    INDEX
    Explanations

    snippets of HTML code, particularly the beginning parts of div blocks and parts of angular directives

    oai_token-act-pair · gemini-2.0-flash

    HTML and CSS code

    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
    /**
    -0.93
     дописавши
    -0.82
     виправивши
    -0.74
    IsContent
    -0.73
    /*
    -0.65
    TagHelper
    -0.64
    sizeCache
    -0.60
     CreateTagHelper
    -0.60
    %)$
    -0.59
     useRef
    -0.57
    POSITIVE LOGITS
    AutoScaleMode
    0.52
     daggers
    0.47
    retudo
    0.47
     abgerufen
    0.46
    //-->
    0.45
    ayaquil
    0.45
     respeito
    0.45
    transQ
    0.44
    SupportActionBar
    0.44
     Inse
    0.44
    Activations Density 1.340%

    No Known Activations