© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 780
    Prev
    Next
    INDEX
    Explanations

    terms found in finance documents

    oai_token-act-pair · gemini-2.0-flash

    investment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Monfieur
    -0.94
    Personendaten
    -0.82
     myſelf
    -0.81
     Efq
    -0.77
     Theſe
    -0.77
     fhew
    -0.76
     Beſ
    -0.72
     chofe
    -0.72
    LookAnd
    -0.71
     $_"
    -0.71
    POSITIVE LOGITS
     desk
    0.42
     Vikipedi
    0.41
    ذ
    0.41
     Signalez
    0.40
     G
    0.39
     .
    0.39
    desk
    0.38
     ra
    0.36
    izoen
    0.36
    자가
    0.36
    Activations Density 3.210%

    No Known Activations