© 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. 12789
    Prev
    Next
    INDEX
    Explanations

    the word "belief" or related words, especially in the context of religion, science, or standards

    oai_token-act-pair · gemini-2.0-flash

    belief

    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
    marginVertical
    -0.71
    frastructure
    -0.69
    colourful
    -0.68
    styrene
    -0.66
    ustainable
    -0.66
     ProtoMessage
    -0.65
    sustainable
    -0.64
    LookAnd
    -0.64
     optimise
    -0.64
     impactful
    -0.63
    POSITIVE LOGITS
    Eloquent
    0.67
     ་་
    0.64
     WebDriverWait
    0.64
    CppMethod
    0.59
     deviceId
    0.57
     épis
    0.56
    tvguidetime
    0.55
     Goodreads
    0.55
     viewDidLoad
    0.54
     uſ
    0.54
    Activations Density 2.220%

    No Known Activations