© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2627
    Prev
    Next
    INDEX
    Explanations

    instances of intensifiers and hyperbole

    oai_token-act-pair · gemini-2.0-flash

    stretching, exaggerating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     AssemblyCompany
    -0.64
     يتيمه
    -0.63
    accharides
    -0.53
    loride
    -0.50
     كومونز
    -0.50
     gemeint
    -0.49
     Offisielt
    -0.49
     '\\;'
    -0.49
    NameInMap
    -0.47
     setw
    -0.47
    POSITIVE LOGITS
     stretch
    0.88
     exaggeration
    0.82
     stretching
    0.79
    stret
    0.77
    stretch
    0.73
     exaggerating
    0.69
     Stretch
    0.68
     exaggerate
    0.67
     exager
    0.67
     Stretching
    0.66
    Activations Density 1.069%

    No Known Activations