© 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. 11571
    Prev
    Next
    INDEX
    Explanations

    scientific writing with mentions of experiments, materials, and results

    oai_token-act-pair · gemini-2.0-flash

    words related to analysis or extraction

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

    analysis and extraction

    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
     Профиль
    -0.51
    Emer
    -0.51
     manuscript
    -0.47
     manuscrit
    -0.46
    IBOutlet
    -0.45
    Closure
    -0.44
     الاطلاع
    -0.43
    erent
    -0.42
    Dataset
    -0.42
     emer
    -0.42
    POSITIVE LOGITS
     analysis
    0.70
     analysing
    0.69
     mergeFrom
    0.68
     analyse
    0.67
     analyze
    0.65
     mix
    0.65
     extracted
    0.65
     analysed
    0.65
     analyzing
    0.65
     extracting
    0.63
    Activations Density 5.245%

    No Known Activations