© 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. 10343
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to geographical features, especially ridges and land formations

    oai_token-act-pair · gemini-2.0-flash

    phrases related to movement and sliding

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

    sliding movement

    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
    otropy
    -0.62
     становника
    -0.62
     VizieR
    -0.61
    AnchorStyles
    -0.60
     ComVisible
    -0.59
     nahilalakip
    -0.57
     unknownFields
    -0.56
     EconPapers
    -0.56
     Timp
    -0.56
    otro
    -0.56
    POSITIVE LOGITS
    shifting
    0.63
     shifting
    0.62
     movement
    0.61
    Glide
    0.57
     sliding
    0.54
     slide
    0.52
     slid
    0.52
     مرئيه
    0.52
    sliding
    0.52
     slides
    0.51
    Activations Density 2.956%

    No Known Activations