© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5784
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets, questions, measurement terms and the word toys

    oai_token-act-pair · gemini-2.0-flash

    Code/documentation snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     sabbia
    -0.48
    atillas
    -0.47
    /***/
    -0.44
    tugas
    -0.43
     römischen
    -0.42
    stellungs
    -0.42
     culoare
    -0.42
     asiática
    -0.41
    engesch
    -0.40
    yym
    -0.39
    POSITIVE LOGITS
    AntiForgeryToken
    0.77
     CreateTagHelper
    0.68
     HasFactory
    0.67
    tonsoft
    0.63
     оригіналу
    0.60
    (!__
    0.59
    NOPQRST
    0.58
    vician
    0.57
     linkovi
    0.57
    PMailer
    0.56
    Activations Density 0.132%

    No Known Activations