© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10496
    Prev
    Next
    INDEX
    Explanations

    references to page numbers from various sources

    oai_token-act-pair · gemini-2.0-flash

    Citations

    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
    انيف
    -0.63
     Wikispecies
    -0.60
     FontFamily
    -0.59
    akam
    -0.57
    postsleuth
    -0.56
    checkable
    -0.56
     Picchu
    -0.54
    örm
    -0.54
    trous
    -0.53
    uleiro
    -0.53
    POSITIVE LOGITS
     Audiodateien
    0.51
     lowlands
    0.51
     esq
    0.51
     anthropologists
    0.50
    Datuak
    0.49
     altars
    0.48
    /**
    0.48
     विश्वसनीयता
    0.48
     blest
    0.47
     ſmall
    0.47
    Activations Density 2.732%

    No Known Activations