© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4397
    Prev
    Next
    INDEX
    Explanations

    HTML header tags, especially those indicating new features or updates in software

    oai_token-act-pair · gemini-2.0-flash

    HTML header tags

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    AccessorTable
    -0.72
     autorytatywna
    -0.71
    ogenen
    -0.63
    webElementXpaths
    -0.58
    ɯ
    -0.54
    extAlignment
    -0.53
    <bos>
    -0.53
    rogen
    -0.51
    Portály
    -0.49
     beginnetje
    -0.47
    POSITIVE LOGITS
     kaynağından
    0.59
     RSSSF
    0.55
     piacere
    0.51
    databind
    0.50
    releases
    0.50
     Britann
    0.50
     bunting
    0.49
    ⓘ
    0.49
     normalement
    0.49
     locket
    0.48
    Activations Density 0.697%

    No Known Activations