© 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. 12551
    Prev
    Next
    INDEX
    Explanations

    blocks of code

    oai_token-act-pair · gemini-2.0-flash

    source code

    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
    wechsel
    -0.45
    cils
    -0.44
    orienti
    -0.44
     repeated
    -0.40
     extent
    -0.40
    VEY
    -0.40
     Cun
    -0.40
    venuto
    -0.40
    باشد
    -0.40
     Wur
    -0.40
    POSITIVE LOGITS
     חיצוניים
    0.86
    NameInMap
    0.83
     kasarigan
    0.82
     ISNI
    0.77
    tvguidetime
    0.74
    Hentet
    0.72
    ViewFeatures
    0.71
    cyklopedia
    0.71
    Παραπομπές
    0.70
     مرئيه
    0.65
    Activations Density 2.271%

    No Known Activations