© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11925
    Prev
    Next
    INDEX
    Explanations

    the word "shut", and words relating to chambers or nozzles.

    oai_token-act-pair · gemini-2.0-flash

    shut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     dedans
    -0.65
     shut
    -0.60
    éndolo
    -0.59
    NUMX
    -0.56
    ceiling
    -0.54
     volon
    -0.54
    Добавлено
    -0.52
    towania
    -0.52
    Quiénes
    -0.51
    ಳ
    -0.51
    POSITIVE LOGITS
    TypedDataSet
    0.75
     <<<<<<<<<<<<<<
    0.60
     apel
    0.54
    <bos>
    0.54
     protoimpl
    0.54
    nodoc
    0.54
    detectChanges
    0.53
    IsContent
    0.53
     uParam
    0.53
    writeFieldEnd
    0.52
    Activations Density 0.970%

    No Known Activations