© 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. 16117
    Prev
    Next
    INDEX
    Explanations

    text from financial regulations

    oai_token-act-pair · gemini-2.0-flash

    Financial obligations and agreements

    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
     Efq
    -1.15
     Reſ
    -1.09
     myſelf
    -1.05
     purpoſe
    -1.01
     itſelf
    -0.99
     Theſe
    -0.98
     Diſ
    -0.97
     Majefty
    -0.94
     ſeveral
    -0.93
     Perſ
    -0.92
    POSITIVE LOGITS
     (
    0.52
     Pro
    0.47
    ific
    0.47
    ,
    0.45
     pro
    0.45
     N
    0.43
     
    0.43
    ance
    0.42
     long
    0.42
    isk
    0.42
    Activations Density 3.747%

    No Known Activations