© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14623
    Prev
    Next
    INDEX
    Explanations

    verbs relating to mixing or changing things up

    oai_token-act-pair · gemini-2.0-flash

    alternating and changing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     мәкал
    -0.82
     inherit
    -0.76
    VIAF
    -0.75
     inher
    -0.71
     heirs
    -0.69
     inherits
    -0.68
    继承
    -0.68
    herit
    -0.67
    MessageOf
    -0.64
    انجليز
    -0.64
    POSITIVE LOGITS
    Portail
    0.58
    fortawesome
    0.52
    ResourceManager
    0.50
     
    0.50
    WindowManager
    0.49
    WireFormatLite
    0.49
    migrationBuilder
    0.48
    MotionEvent
    0.48
    נטרנט
    0.47
    CppMethod
    0.46
    Activations Density 1.412%

    No Known Activations