© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4201
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

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

    references to divine authority

    oai_token-act-pair · gemini-2.0-flash

    Giving, applying

    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
     inherits
    -0.63
    Losing
    -0.60
    losing
    -0.59
     bekommen
    -0.58
     recieve
    -0.57
     erhalten
    -0.57
     krijgen
    -0.57
     erfahren
    -0.56
    obtain
    -0.55
     иметь
    -0.55
    POSITIVE LOGITS
     gave
    0.81
    ोंने
    0.73
     took
    0.62
     did
    0.60
     changed
    0.60
     समीक्षक
    0.59
     نے
    0.58
     ने
    0.58
     put
    0.58
     threw
    0.57
    Activations Density 1.903%

    No Known Activations