© 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. 8404
    Prev
    Next
    INDEX
    Explanations

    durations of time and ordinal numbers within a period of time

    oai_token-act-pair · gemini-2.0-flash

    consecutive

    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
    RegistryLite
    -0.73
    ScopeManager
    -0.71
    rrggbb
    -0.69
     protoimpl
    -0.64
    GEBURTSDATUM
    -0.61
     مشين
    -0.60
    expandindo
    -0.59
    دانشنامهٔ
    -0.58
     avoient
    -0.57
    HtmlAttribute
    -0.56
    POSITIVE LOGITS
     consecutive
    1.93
     consecu
    1.51
     successive
    1.48
     consecutively
    1.42
     straight
    1.38
     succession
    1.30
    连续
    1.21
     continuous
    1.20
     sequential
    1.15
    連続
    1.13
    Activations Density 0.989%

    No Known Activations