© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3312
    Prev
    Next
    INDEX
    Explanations

    the word "manual"

    oai_token-act-pair · gemini-2.0-flash

    manual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    AndEndTag
    -1.53
    IntoConstraints
    -1.30
    SharedDtor
    -1.27
    ItemBackground
    -1.26
    InjectAttribute
    -1.23
    GEBURTSDATUM
    -1.23
     GenerationType
    -1.23
     typelib
    -1.22
    LookAnd
    -1.21
    DockStyle
    -1.16
    POSITIVE LOGITS
    ↵
    0.67
    F
    0.66
    S
    0.65
    -
    0.65
    I
    0.63
    H
    0.59
    A
    0.58
    /
    0.57
    V
    0.57
    )
    0.56
    Activations Density 0.761%

    No Known Activations