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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13410
    Prev
    Next
    INDEX
    Explanations

    the term "Al" followed by a word related to a Middle Eastern place or name

    oai_token-act-pair · gemini-2.0-flash

    Al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Al
    -2.59
    Al
    -2.33
     al
    -2.05
     AL
    -1.77
    AL
    -1.27
     Аль
    -1.23
    アル
    -1.20
    al
    -1.19
    Аль
    -1.16
     аль
    -1.16
    POSITIVE LOGITS
    tvguidetime
    0.62
    quartile
    0.54
    brin
    0.54
    Попис
    0.52
    }}}
    
    0.51
     neceffary
    0.50
    LabelTagHelper
    0.48
     Inscrivez
    0.48
     CreateTagHelper
    0.48
    ificazione
    0.48
    Activations Density 4.052%

    No Known Activations