© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1425
    Prev
    Next
    INDEX
    Explanations

    words related to modifying a profile

    oai_token-act-pair · gemini-2.0-flash

    User interfaces and software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Халык
    -0.62
     gué
    -0.52
    algebra
    -0.51
    rza
    -0.49
     fréqu
    -0.49
     minerales
    -0.49
     تضيفلها
    -0.49
    PerformLayout
    -0.47
     béné
    -0.47
     gehouden
    -0.47
    POSITIVE LOGITS
    aryen
    0.67
     صوتيه
    0.65
    <bos>
    0.64
     BoxDecoration
    0.64
    yntaxException
    0.60
     CommonModule
    0.58
    endpush
    0.56
    enumi
    0.54
    labus
    0.54
     contextLoads
    0.54
    Activations Density 3.869%

    No Known Activations