© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6792
    Prev
    Next
    INDEX
    Explanations

    the word "certain" and related words

    oai_token-act-pair · gemini-2.0-flash

    certain

    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
     in
    -0.78
    ,
    -0.77
     and
    -0.74
     as
    -0.71
     at
    -0.70
     whilst
    -0.69
     It
    -0.68
     We
    -0.65
     with
    -0.62
    Whilst
    -0.62
    POSITIVE LOGITS
    ]--;
    0.96
     Theſe
    0.86
     Houſe
    0.85
     Beſ
    0.79
     ―――――
    0.75
    Искәрмәләр
    0.74
     Monfieur
    0.74
    — 
    0.73
    utilisons
    0.73
     {}",
    0.73
    Activations Density 2.214%

    No Known Activations