© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8743
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and words that signal an explanation is occurring

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    lography
    -0.60
    corer
    -0.58
    клопе
    -0.56
    intios
    -0.54
    tainable
    -0.52
    rl
    -0.51
    Hochspringen
    -0.50
    AutoField
    -0.49
    rig
    -0.49
    mel
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.69
     onBind
    0.64
    出版年
    0.59
     насељу
    0.57
    __(/*!
    0.56
    хьтан
    0.56
     ännu
    0.55
     fumée
    0.55
    //</
    0.54
    ToScroll
    0.54
    Activations Density 0.343%

    No Known Activations