© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9674
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to making judgements and qualifying statements

    oai_token-act-pair · gemini-2.0-flash

    say

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ❸
    -0.40
    bek
    -0.39
     Variability
    -0.39
     circonst
    -0.38
    All
    -0.38
    atka
    -0.38
     thế
    -0.38
     vocale
    -0.38
     précise
    -0.36
     estabilidad
    -0.36
    POSITIVE LOGITS
    migrationBuilder
    0.84
     downright
    0.76
    NgModule
    0.76
     تعدى
    0.76
    RefNanny
    0.74
    ')['
    0.73
    esModule
    0.71
    BrowserModule
    0.71
    __":
    0.69
     للمعارف
    0.65
    Activations Density 1.774%

    No Known Activations