© 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. 5463
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related discussions, possibly in Python, with focus on API and decorators

    oai_token-act-pair · gemini-2.0-flash

    Code and APIs

    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
     محفوظة
    -0.64
     насељу
    -0.63
    CppCodeGen
    -0.60
    featureID
    -0.59
     становника
    -0.57
     Abbe
    -0.57
    mercato
    -0.57
     Majefty
    -0.57
    Hozzáférés
    -0.57
    enedig
    -0.56
    POSITIVE LOGITS
     conto
    0.53
     Men
    0.47
    exitRule
    0.47
     AspNetCore
    0.45
     welcome
    0.44
    yet
    0.44
     Под
    0.44
    TagHelpers
    0.44
     get
    0.43
     salad
    0.42
    Activations Density 10.316%

    No Known Activations