© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5529
    Prev
    Next
    INDEX
    Explanations

    latex math combined with numbered lists

    oai_token-act-pair · gemini-2.0-flash

    Exponents and ordinal numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Ce
    -0.45
    Pron
    -0.45
    erra
    -0.42
     Kra
    -0.42
    ayer
    -0.42
    AccessFile
    -0.42
     Tru
    -0.42
     pron
    -0.41
    ady
    -0.40
    atoria
    -0.40
    POSITIVE LOGITS
    PerformLayout
    0.74
     évêque
    0.68
    الحياه
    0.67
     feroit
    0.66
     étoit
    0.65
    ieteur
    0.65
     Administrativna
    0.64
     chré
    0.64
    ագրություններ
    0.63
    Hentet
    0.63
    Activations Density 0.560%

    No Known Activations