© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8063
    Prev
    Next
    INDEX
    Explanations

    the word 'the', the word 'first' and some common verbs

    oai_token-act-pair · gemini-2.0-flash

    technical terminology or programming-related terms

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

    beginnings, reasons

    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
     quæ
    -0.65
     ejus
    -0.54
     />);
    -0.52
     بيها
    -0.49
     deſt
    -0.49
     reafon
    -0.48
     "'");
    -0.48
     reaſon
    -0.48
     salto
    -0.47
    IsContent
    -0.47
    POSITIVE LOGITS
    قایناق‌لار
    0.72
    ReusableCell
    0.71
     مرئيه
    0.67
     onOptions
    0.63
     ComVisible
    0.56
    المناصب
    0.55
    phosa
    0.55
    TargetException
    0.53
     linkovi
    0.52
    FontWeight
    0.52
    Activations Density 1.352%

    No Known Activations