© 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. 4302
    Prev
    Next
    INDEX
    Explanations

    the word "stable" and, to a lesser extent, words related to duration

    oai_token-act-pair · gemini-2.0-flash

    stable

    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
    ↵↵
    -0.66
    <h3>
    -0.62
     
    -0.60
    The
    -0.56
     the
    -0.54
    b
    -0.54
    ed
    -0.54
    <eos>
    -0.53
     latine
    -0.53
    For
    -0.52
    POSITIVE LOGITS
    ="@+
    1.11
    XmlAccessType
    1.02
    ArgsConstructor
    1.01
     MainAxisSize
    1.01
    BagConstraints
    1.00
    ChildScrollView
    0.99
    ConstraintMaker
    0.98
     GenerationType
    0.98
    RectangleBorder
    0.95
    NUMX
    0.94
    Activations Density 2.091%

    No Known Activations