© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2547
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives that intensify other words

    oai_token-act-pair · gemini-2.0-flash

    highly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     highly
    -1.71
    highly
    -1.59
    Highly
    -1.55
     Highly
    -1.49
     altamente
    -1.09
    <bos>
    -1.08
     heavily
    -0.92
     hugely
    -0.86
     extremely
    -0.79
     strongly
    -0.71
    POSITIVE LOGITS
     TestBed
    0.65
    ItemBackground
    0.64
    TagMode
    0.62
    AutoresizingMask
    0.60
    remes
    0.59
    Kontrola
    0.58
     protoimpl
    0.57
     CreateTagHelper
    0.57
    tvguidetime
    0.54
     Lumpur
    0.53
    Activations Density 4.572%

    No Known Activations