© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4345
    Prev
    Next
    INDEX
    Explanations

    code snippets and related problem-solving discourse

    oai_token-act-pair · gemini-2.0-flash

    database queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     للاسماء
    -0.63
     enriquec
    -0.52
     sélectionnés
    -0.51
     skriva
    -0.50
    ConstraintMaker
    -0.50
     witches
    -0.49
    openSession
    -0.49
    Tracce
    -0.49
     äta
    -0.49
    andExpect
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.65
    ⓧ
    0.64
    afficheront
    0.57
    contentLoaded
    0.53
    thâu
    0.52
    PerformLayout
    0.52
     AssemblyCulture
    0.51
     estimés
    0.51
    verwijspagina
    0.50
     EconPapers
    0.50
    Activations Density 1.302%

    No Known Activations