© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9443
    Prev
    Next
    INDEX
    Explanations

    the word "strength", sometimes in the context of material properties or capabilities

    oai_token-act-pair · gemini-2.0-flash

    strength

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     strength
    -3.02
    strength
    -2.70
     Strength
    -2.69
    Strength
    -2.61
     STRENGTH
    -2.44
     strengths
    -2.27
    STRENGTH
    -2.19
     Strengths
    -1.97
     stronger
    -1.82
     streng
    -1.77
    POSITIVE LOGITS
    IntoConstraints
    0.66
    يكب
    0.54
    êmio
    0.44
    liferay
    0.42
     álla
    0.41
     rodo
    0.40
    kini
    0.40
    jLabel
    0.40
     cristales
    0.40
    lieb
    0.40
    Activations Density 0.797%

    No Known Activations