© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13158
    Prev
    Next
    INDEX
    Explanations

    terms related to theoretical physics and material science, especially superconductivity

    oai_token-act-pair · gemini-2.0-flash

    coffee

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    })));
    -0.63
     complètes
    -0.61
     alimentaires
    -0.59
    สือ
    -0.59
    帖最后由
    -0.56
    ctrica
    -0.56
     snippetHide
    -0.56
    Vezi
    -0.56
     Tetrahedron
    -0.55
    Neden
    -0.54
    POSITIVE LOGITS
     lat
    0.57
    COUVER
    0.51
    PreferredItem
    0.51
     bar
    0.50
    bar
    0.50
     '{@
    0.48
     капу
    0.48
    RTCF
    0.47
    crollView
    0.47
    base
    0.47
    Activations Density 1.292%

    No Known Activations