© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2120
    Prev
    Next
    INDEX
    Explanations

    a diverse set of verbs, but consistently activates on "get," and other words indicating action or states of being.

    oai_token-act-pair · gemini-2.0-flash

    get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    FormBuilder
    -0.54
    isContained
    -0.52
    astéroïdes
    -0.46
    tvrt
    -0.40
    zaamheid
    -0.40
    łaj
    -0.39
     Потому
    -0.37
    RTDA
    -0.36
    ModelBuilder
    -0.36
    érial
    -0.36
    POSITIVE LOGITS
    AddTagHelper
    0.69
    OGND
    0.67
    WebVitals
    0.66
    RetentionPolicy
    0.66
    eleste
    0.59
    bando
    0.59
     Meksiku
    0.58
    __*/
    0.58
    ropractor
    0.57
    المشاركات
    0.57
    Activations Density 8.098%

    No Known Activations