© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14643
    Prev
    Next
    INDEX
    Explanations

    a paragraph starting with a newline preceded by several newlines/whitespace (or at the start of the document), then finds patterns of certain common and frequent short words and punctuation marks

    oai_token-act-pair · gemini-2.0-flash

    Programs

    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
    ngrx
    -0.56
     TextInputType
    -0.53
    KommentareTeilen
    -0.53
     createSprite
    -0.50
    PROFESSIONAL
    -0.50
     NgModule
    -0.49
    ạch
    -0.49
    Wiel
    -0.48
    ########.
    -0.48
     professionally
    -0.48
    POSITIVE LOGITS
     program
    1.46
     programs
    1.27
     Program
    1.27
    program
    1.27
     programme
    1.25
    Program
    1.20
     PROGRAM
    1.16
     programa
    1.16
    programs
    1.15
     programmes
    1.13
    Activations Density 1.819%

    No Known Activations