© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11931
    Prev
    Next
    INDEX
    Explanations

    disclaimers and customer service statements for online retailers

    oai_token-act-pair · gemini-2.0-flash

    indications of terms related to privacy and security policies

    np_token-act-pair-logits · gpt-4o-mini

    legal/company statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    getHeaders
    -0.58
    Пото
    -0.57
     ostavi
    -0.52
    خواندن
    -0.52
     للاسماء
    -0.50
     "").
    -0.50
     SafeMath
    -0.49
     }</
    -0.49
    })();
    -0.49
    atmosfera
    -0.48
    POSITIVE LOGITS
     follow
    0.56
     مشين
    0.54
     reserve
    0.52
    EndGlobalSection
    0.50
     henvis
    0.50
     adopt
    0.49
    ENUM
    0.48
    rebbero
    0.48
    modb
    0.48
     viewDidLoad
    0.47
    Activations Density 1.677%

    No Known Activations