© 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. 10293
    Prev
    Next
    INDEX
    Explanations

    comparative descriptions, especially those involving percentages and heat

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
     high
    -1.00
     intensive
    -0.99
     excessive
    -0.98
    intensive
    -0.98
     heavy
    -0.97
    extensive
    -0.96
    high
    -0.96
     highest
    -0.94
     Extensive
    -0.94
     extreme
    -0.94
    POSITIVE LOGITS
    قایناق‌لار
    0.58
    ogaster
    0.50
    ագրություններ
    0.47
    idigung
    0.46
    Hentet
    0.45
    fromCharCode
    0.45
     PopupWindow
    0.44
    LLocation
    0.43
    Palindrome
    0.42
    хара
    0.41
    Activations Density 3.653%

    No Known Activations