© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4141
    Prev
    Next
    INDEX
    Explanations

    words related to degree and severity of an event

    oai_token-act-pair · gemini-2.0-flash

    severity

    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
    Clik
    -0.60
    __':
    -0.59
     cherchés
    -0.59
     linkovi
    -0.59
    ьаж
    -0.59
    domada
    -0.57
    tanooga
    -0.55
    mybatisplus
    -0.55
     referrerpolicy
    -0.54
     utafitiHapana
    -0.53
    POSITIVE LOGITS
     severe
    1.37
    severe
    1.23
     extreme
    1.09
    Severe
    1.06
     Severe
    1.05
     serious
    0.99
     sév
    0.90
    extreme
    0.89
     severely
    0.87
     sever
    0.86
    Activations Density 1.518%

    No Known Activations