© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9572
    Prev
    Next
    INDEX
    Explanations

    the string "Rec", often followed by a lowercase letter or digit

    oai_token-act-pair · gemini-2.0-flash

    Rec

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tvguidetime
    -0.89
    下载附件
    -0.77
    DockStyle
    -0.77
    httphttps
    -0.77
     uintptr
    -0.75
    ChildScrollView
    -0.74
    +#+
    -0.73
     initComponents
    -0.73
    matchCondition
    -0.73
     AssemblyCulture
    -0.72
    POSITIVE LOGITS
    lasma
    0.45
     Personal
    0.39
    lass
    0.39
    ruiter
    0.39
    doms
    0.38
     personal
    0.37
    ite
    0.37
     kon
    0.35
    Personal
    0.34
     sk
    0.34
    Activations Density 1.041%

    No Known Activations