© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9814
    Prev
    Next
    INDEX
    Explanations

    mentions of liquid assets

    oai_token-act-pair · gemini-2.0-flash

    financial terms related to cash

    np_token-act-pair-logits · gpt-4o-mini

    cash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     joaat
    -0.44
    του
    -0.43
    ポーター
    -0.42
     famiglie
    -0.40
    ResourceManager
    -0.40
    mtable
    -0.40
     ảnh
    -0.38
    diğinde
    -0.37
    HtmlAttribute
    -0.37
    databinding
    -0.36
    POSITIVE LOGITS
    rungsseite
    0.76
     nakalista
    0.75
    protoimpl
    0.73
    InvalidProtocol
    0.73
    Билгалдахарш
    0.69
    مصادر
    0.69
    లాలు
    0.65
     насељу
    0.64
    Viited
    0.62
    nologue
    0.61
    Activations Density 0.613%

    No Known Activations