© 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. 9668
    Prev
    Next
    INDEX
    Explanations

    the word "tens" or variations of it, often in a numerical context or company name

    oai_token-act-pair · gemini-2.0-flash

    tens

    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
     magique
    -0.64
    '
    -0.61
     elettron
    -0.59
     poire
    -0.54
     africaine
    -0.54
     vanille
    -0.54
     insegu
    -0.53
    값
    -0.53
    Security
    -0.52
     cilind
    -0.52
    POSITIVE LOGITS
    cupa
    0.73
    OrBuilder
    0.73
    InputBorder
    0.68
    kapat
    0.65
    BeginInit
    0.65
    ArgsConstructor
    0.64
    borderSide
    0.63
     Zacks
    0.62
     AppComponent
    0.60
    LookAnd
    0.59
    Activations Density 1.648%

    No Known Activations