© 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. 10732
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    EDEFAULT
    -0.99
     autorytatywna
    -0.98
     AssemblyCompany
    -0.93
     Roskov
    -0.92
    NewUrlParser
    -0.91
     متعلقه
    -0.90
    IUrlHelper
    -0.90
     оригіналу
    -0.90
     חיצוניים
    -0.89
    IntoConstraints
    -0.89
    POSITIVE LOGITS
    GetMapping
    0.36
    ++
    0.36
    4
    0.34
    рок
    0.33
    RPC
    0.33
    0.31
    1
    0.31
    vá
    0.30
     elektr
    0.30
    GC
    0.30
    Activations Density 0.768%
    No Known Activations