© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3353
    Prev
    Next
    INDEX
    Explanations

    words that describe industry, production, and companies

    oai_token-act-pair · gemini-2.0-flash

    manufacturer or reputation

    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
    etheless
    -1.01
    ousands
    -0.90
    hematical
    -0.89
    nadequate
    -0.89
    ousand
    -0.87
    IFORN
    -0.87
    frastructure
    -0.85
    lidene
    -0.84
    withstanding
    -0.84
    calypse
    -0.81
    POSITIVE LOGITS
    <bos>
    0.62
    er
    0.59
    ar
    0.56
    Siehe
    0.50
    he
    0.49
    en
    0.49
    self
    0.49
     “
    0.47
     Usted
    0.47
    til
    0.46
    Activations Density 0.509%

    No Known Activations