© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7120
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strength" or "strong" and related words.

    oai_token-act-pair · gemini-2.0-flash

    Strength/Strong

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ChildScrollView
    -0.86
     itſelf
    -0.83
    ſelf
    -0.74
     myſelf
    -0.70
    MLLoader
    -0.69
    LookAnd
    -0.65
    Configurer
    -0.62
    !("{}",
    -0.62
    __":
    -0.61
    DockStyle
    -0.60
    POSITIVE LOGITS
    STRONG
    0.88
     Strong
    0.85
     weak
    0.82
    Strong
    0.81
     strong
    0.81
     stronger
    0.75
     Weak
    0.75
     Stronger
    0.73
    weak
    0.72
    strong
    0.71
    Activations Density 0.593%

    No Known Activations