© 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. 15156
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 'ing' as well as some prepositions that follow

    oai_token-act-pair · gemini-2.0-flash

    words ending in -ing

    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
     păr
    -0.57
     leçon
    -0.56
     cauza
    -0.56
     científicas
    -0.55
     vanskelig
    -0.54
    ônicos
    -0.54
     femininas
    -0.54
     tchèque
    -0.54
     prieten
    -0.53
     médicas
    -0.52
    POSITIVE LOGITS
    expandindo
    0.92
     виправивши
    0.87
    IntoConstraints
    0.81
    DockStyle
    0.81
     Мексичка
    0.69
    <?
    0.66
    opsida
    0.65
    sidemargin
    0.65
    ⓧ
    0.63
    RegressionTest
    0.62
    Activations Density 2.871%

    No Known Activations