© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11347
    Prev
    Next
    INDEX
    Explanations

    conversation in the third person and names of people.

    oai_token-act-pair · gemini-2.0-flash

    Quotes from people

    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
    disposing
    -0.50
    הערות
    -0.47
     ModelExpression
    -0.46
    >//
    -0.46
    tvguidetime
    -0.46
     kasarigan
    -0.45
     StringTokenizer
    -0.45
     }{@
    -0.45
     hậu
    -0.44
    culable
    -0.44
    POSITIVE LOGITS
    ViewFeatures
    0.59
    ItemBackground
    0.59
    دانشنامهٔ
    0.56
     Normdatei
    0.55
    oa̍t
    0.54
    katapos
    0.54
    іга
    0.54
    itename
    0.53
    AsStream
    0.53
     אות
    0.52
    Activations Density 1.509%

    No Known Activations