© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10067
    Prev
    Next
    INDEX
    Explanations

    adjectives modified by "very" or "really", and related adverbs

    oai_token-act-pair · gemini-2.0-flash

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    OGND
    -0.55
     onOptions
    -0.54
    TestingModule
    -0.52
    onOptions
    -0.52
     تضيفلها
    -0.49
    日閲覧
    -0.49
     OnTriggerEnter
    -0.48
     contextLoads
    -0.46
    lowest
    -0.46
    ViewInit
    -0.46
    POSITIVE LOGITS
    enumii
    0.66
    phosa
    0.58
     nghĩa
    0.57
    entiary
    0.56
    Демографія
    0.55
    '])->
    0.52
    CodeAttribute
    0.50
    libft
    0.50
     المعيارى
    0.49
    ually
    0.49
    Activations Density 0.354%

    No Known Activations