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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4582
    Prev
    Next
    INDEX
    Explanations

    sequences of letters and numbers, possibly video ids

    oai_token-act-pair · gemini-2.0-flash

    technical contexts, URLs, code

    np_max-act-logits · 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
     ostavi
    -0.89
    msgSender
    -0.84
    homonymie
    -0.80
    InputTagHelper
    -0.78
     "];
    -0.75
    elemField
    -0.69
    ^(@)
    -0.68
    ]';
    -0.68
    — 
    -0.67
     Logement
    -0.67
    POSITIVE LOGITS
    _
    1.42
    \_
    0.83
     _
    0.58
    wyt
    0.37
    ooc
    0.36
    ус
    0.36
     reap
    0.36
    //_
    0.36
    avad
    0.35
     kore
    0.35
    Activations Density 0.414%

    No Known Activations