© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13056
    Prev
    Next
    INDEX
    Explanations

    the word "all" or phrases ending in "all"

    oai_token-act-pair · gemini-2.0-flash

    all

    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
     at
    -0.59
    ConstraintMaker
    -0.58
     @"/
    -0.55
     performances
    -0.53
    reras
    -0.52
     τί
    -0.52
     éditoriale
    -0.51
    ddots
    -0.51
    ogueira
    -0.50
     poziomie
    -0.50
    POSITIVE LOGITS
    ModelSerializer
    0.63
    PostExecute
    0.56
    NameInMap
    0.55
     Shady
    0.54
    存于互联网档案馆
    0.54
     OFDb
    0.53
    GOTREF
    0.53
    vrigt
    0.51
    iją
    0.51
    onAttach
    0.50
    Activations Density 1.449%

    No Known Activations