© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5383
    Prev
    Next
    INDEX
    Explanations

    mentions of experiments and experimental procedures

    oai_token-act-pair · gemini-2.0-flash

    experiment

    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
    ^(@)
    -1.00
     doubtnut
    -0.96
    nologue
    -0.92
     Efq
    -0.84
    Öffnungszeiten
    -0.83
    OOTDTY
    -0.80
    {?>
    -0.79
     sanitaires
    -0.79
    <bos>
    -0.78
     vectorielles
    -0.78
    POSITIVE LOGITS
    0.61
    0.60
    oa̍t
    0.60
    .
    0.59
    Her
    0.57
    Du
    0.57
    ViewFeatures
    0.56
                                
    0.54
    TO
    0.52
     Пла
    0.52
    Activations Density 0.714%

    No Known Activations