© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12036
    Prev
    Next
    INDEX
    Explanations

    words and phrases about something being lost, broken, dead, or otherwise defective

    oai_token-act-pair · gemini-2.0-flash

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ngdoc
    -0.79
     eventdata
    -0.69
    WRENCE
    -0.66
     مرئيه
    -0.63
     ✭✭
    -0.62
    Personendaten
    -0.59
     ostavi
    -0.59
    copg
    -0.57
    jsii
    -0.57
    findpost
    -0.57
    POSITIVE LOGITS
     gewohnt
    0.52
     "}";
    0.49
    новременно
    0.47
    dyti
    0.45
    ?):
    0.44
     nguyễn
    0.43
     Nachfolger
    0.42
     Redacción
    0.41
    "';
    0.41
    altro
    0.40
    Activations Density 1.013%

    No Known Activations