© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10348
    Prev
    Next
    INDEX
    Explanations

    descriptions of powers and abilities

    oai_token-act-pair · gemini-2.0-flash

    Kyutama

    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
    AddTagHelper
    -0.67
    发表于
    -0.60
    posedge
    -0.60
    -------------</
    -0.59
     BoxFit
    -0.56
    ledem
    -0.56
    ']>;
    -0.56
    sozial
    -0.55
    tvguidetime
    -0.55
    AddHtmlAttribute
    -0.54
    POSITIVE LOGITS
    Portale
    0.62
    engan
    0.52
    InitVars
    0.50
    clic
    0.49
    lerp
    0.46
    carte
    0.45
    ImageField
    0.45
    ьаж
    0.45
    istiques
    0.44
    体
    0.43
    Activations Density 5.891%

    No Known Activations