© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9120
    Prev
    Next
    INDEX
    Explanations

    an assortment of words and phrases that have to do with correctness and judgement, as well as some blog-related terminology

    oai_token-act-pair · gemini-2.0-flash

    positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    /**
    -0.68
    <bos>
    -0.65
    genöss
    -0.61
    Đây
    -0.59
    Dette
    -0.59
    agissait
    -0.58
    utilisons
    -0.58
    那是
    -0.58
     surla
    -0.57
    슷
    -0.57
    POSITIVE LOGITS
    jsdelivr
    0.65
     forKey
    0.59
    principalTable
    0.56
    einander
    0.55
    Pile
    0.51
    WriteAttribute
    0.50
    odha
    0.50
     */
    0.49
    setVerticalGroup
    0.48
     audiobooks
    0.48
    Activations Density 0.675%

    No Known Activations