© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11940
    Prev
    Next
    INDEX
    Explanations

    the word "moon", sometimes in conjunction with "sun" and "yourself"

    oai_token-act-pair · gemini-2.0-flash

    moon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ge
    -0.52
    SharedCtor
    -0.51
    SizeMode
    -0.51
    .
    -0.50
    χρι
    -0.50
    ↵↵
    -0.49
     once
    -0.49
    @
    -0.49
     rate
    -0.48
    >
    -0.48
    POSITIVE LOGITS
    =$?
    0.87
     itſelf
    0.84
    OGND
    0.83
    EDEFAULT
    0.82
    ^(@)
    0.81
    Ecotoxicity
    0.79
    PointerException
    0.77
    liesslich
    0.77
     Efq
    0.77
    CORBA
    0.76
    Activations Density 1.306%

    No Known Activations