© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4230
    Prev
    Next
    INDEX
    Explanations

    text pertaining to finances and energy bills

    oai_token-act-pair · gemini-2.0-flash

    money

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    !*\
    -0.82
    Diweddarwch
    -0.82
    ^(@)
    -0.81
     &___
    -0.81
     uintptr
    -0.79
    ")));
    -0.78
     Efq
    -0.76
    +#+#
    -0.76
    didSet
    -0.75
     surla
    -0.75
    POSITIVE LOGITS
    <eos>
    0.44
    3
    0.41
    (
    0.40
    ↵
    0.40
                        
    0.39
    гии
    0.39
    ((
    0.37
    <sup>
    0.37
    2
    0.37
    *
    0.37
    Activations Density 2.082%

    No Known Activations