© 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. 15978
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming language constructs

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     myſelf
    -1.38
     Efq
    -1.37
     BoxFit
    -1.33
     ſind
    -1.30
    Personendaten
    -1.28
     ་་
    -1.28
    ſelves
    -1.27
     propOrder
    -1.26
     itſelf
    -1.26
     Majefty
    -1.26
    POSITIVE LOGITS
    ,
    1.07
     
    0.98
     (
    0.85
    ↵↵
    0.83
    -
    0.81
    (
    0.79
    .
    0.79
    0
    0.75
    1
    0.75
    ;
    0.74
    Activations Density 49.218%

    No Known Activations