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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14415
    Prev
    Next
    INDEX
    Explanations

    large numbers, especially those including exponents, percentages, or those that specify ratios or measurements

    oai_token-act-pair · gemini-2.0-flash

    potentially archaic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     
    -1.20
    ,
    -1.16
    .
    -1.14
     (
    -1.14
    ↵
    -1.13
    <eos>
    -1.08
    ↵↵
    -1.08
    -
    -1.07
    2
    -1.07
    '
    -1.06
    POSITIVE LOGITS
     Efq
    2.13
     Theſe
    2.03
     myſelf
    1.98
     Monfieur
    1.88
     itſelf
    1.85
     Jefus
    1.77
    ſelf
    1.76
     purpoſe
    1.74
     pleaſure
    1.74
     Anſ
    1.73
    Activations Density 2.212%

    No Known Activations