© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3024
    Prev
    Next
    INDEX
    Explanations

    code declaring arrays of numbers

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     var
    -2.47
    Var
    -2.33
    var
    -2.31
     variable
    -2.28
     Variable
    -2.25
     Var
    -2.23
    VAR
    -2.17
    variable
    -2.13
    Variable
    -2.13
     Vari
    -2.13
    POSITIVE LOGITS
     resourceCulture
    0.59
    ----</
    0.58
    didSet
    0.55
     Pons
    0.52
    SpringBoot
    0.52
    Cyfarwyddwr
    0.51
    Dreaming
    0.50
    Референце
    0.49
     Duckworth
    0.49
    EDEFAULT
    0.48
    Activations Density 4.429%

    No Known Activations