© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10690
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions, forms of the verb "to be", and punctuation.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or identifiers

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     is
    -1.25
     are
    -1.02
     be
    -0.84
     là
    -0.77
    のが
    -0.77
     être
    -0.76
    are
    -0.74
     was
    -0.74
     essere
    -0.73
     Are
    -0.66
    POSITIVE LOGITS
     EconPapers
    1.26
    ConstraintMaker
    0.90
    OGND
    0.90
     AttributeSet
    0.86
     myſelf
    0.85
     SafeArea
    0.81
    ]--;
    0.81
    setVerticalGroup
    0.81
     raiſ
    0.80
    styleable
    0.80
    Activations Density 2.888%

    No Known Activations