© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11872
    Prev
    Next
    INDEX
    Explanations

    positive conjunctions and words that amplify adjectives

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     HttpNotFound
    -0.57
     MainAxisSize
    -0.56
    aarrggbb
    -0.56
    UnusedPrivate
    -0.55
    homonymie
    -0.52
    хьтан
    -0.52
    addContainerGap
    -0.51
     Productive
    -0.50
    latego
    -0.49
    ]++;
    -0.49
    POSITIVE LOGITS
     سكانية
    0.54
     it
    0.52
     egne
    0.49
    ummer
    0.49
    MessageTagHelper
    0.47
    DispatchToProps
    0.47
     nôtre
    0.46
     ň
    0.46
     keb
    0.46
     passaggio
    0.46
    Activations Density 9.239%

    No Known Activations