© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4943
    Prev
    Next
    INDEX
    Explanations

    code syntax, especially related to API requests and data handling, possibly in Java or a similar language, along with array manipulations and string formatting in another language.

    oai_token-act-pair · gemini-2.0-flash

    Code 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
    Personendaten
    -1.38
     itſelf
    -1.23
    OGND
    -1.21
    IntoConstraints
    -1.20
     ExecuteAsync
    -1.18
    RenderAtEndOf
    -1.17
     CURIAM
    -1.14
     незавершена
    -1.14
    NUMX
    -1.13
    MemoryWarning
    -1.12
    POSITIVE LOGITS
     
    0.64
     !
    0.47
    <eos>
    0.47
     it
    0.47
     a
    0.46
     di
    0.46
     i
    0.45
     id
    0.45
     op
    0.45
     Long
    0.44
    Activations Density 3.025%

    No Known Activations