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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7344
    Prev
    Next
    INDEX
    Explanations

    content markers like figures and section headers

    oai_token-act-pair · gemini-2.0-flash

    Fig

    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
    <bos>
    -1.63
    The
    -0.94
    ↵↵
    -0.94
    ↵
    -0.92
    <strong>
    -0.89
    <em>
    -0.85
    is
    -0.84
    <b>
    -0.82
    In
    -0.79
    and
    -0.79
    POSITIVE LOGITS
     CreateTagHelper
    1.29
     виправивши
    1.19
    :✨
    1.16
     autorytatywna
    1.09
     Roskov
    1.09
    lgari
    1.07
    XmlAccessType
    1.06
     betweenstory
    1.06
    drawal
    1.05
     resourceCulture
    1.05
    Activations Density 1.804%

    No Known Activations