© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15907
    Prev
    Next
    INDEX
    Explanations

    proper nouns and version numbers

    oai_token-act-pair · gemini-2.0-flash

    software and analytics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     ویکی‌پدیا
    -0.75
     Wiktionnaire
    -0.60
    وفة
    -0.59
     ujednoznacz
    -0.58
     оригинала
    -0.57
     Majefty
    -0.54
     Sciento
    -0.54
     Unito
    -0.54
     reafon
    -0.53
    ISupport
    -0.53
    POSITIVE LOGITS
    <bos>
    0.76
    SharedCtor
    0.63
    BufferException
    0.60
    RegressionTest
    0.58
    stdc
    0.57
    DrawerToggle
    0.56
     continúas
    0.55
    ngdoc
    0.50
    requireNonNull
    0.50
    Ặ
    0.48
    Activations Density 2.761%

    No Known Activations