© 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. 5174
    Prev
    Next
    INDEX
    Explanations

    several different word stems like "diret", "documenta", "posi", "kor", and "pita"

    oai_token-act-pair · gemini-2.0-flash

    code, foreign languages, technical

    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
     existing
    -0.48
    ج
    -0.47
    puta
    -0.47
    тики
    -0.47
    IPE
    -0.47
     azi
    -0.45
     extruded
    -0.45
     spoil
    -0.45
     урна
    -0.44
    gula
    -0.44
    POSITIVE LOGITS
    ContentAsync
    0.81
    VolleyError
    0.75
    tagHelperRunner
    0.70
     שוליים
    0.69
     للاسماء
    0.69
     typelib
    0.64
    IonicModule
    0.63
     سكانية
    0.62
    cjach
    0.57
     препратки
    0.57
    Activations Density 5.512%

    No Known Activations