Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7428
    Prev
    Next
    INDEX
    Explanations

    mentions of recent or past weather

    oai_token-act-pair · gemini-2.0-flash

    weather

    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
     myſelf
    -2.34
     Monfieur
    -2.14
     Theſe
    -2.14
     pleaſure
    -2.13
     Efq
    -2.13
     purpoſe
    -2.09
     houſe
    -2.03
     Majefty
    -2.00
     itſelf
    -1.99
     ſtate
    -1.97
    POSITIVE LOGITS
    ↵↵
    1.42
     
    1.42
     A
    1.34
     The
    1.34
     (
    1.26
     In
    1.24
     C
    1.23
    ↵
    1.20
     I
    1.20
     S
    1.16
    Activations Density 3.396%

    No Known Activations