© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16104
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in product reviews or technical discussions, particularly those involving comparisons.

    oai_token-act-pair · gemini-2.0-flash

    developer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     themſelves
    -0.52
     himſelf
    -0.52
    itarios
    -0.52
    󠁣
    -0.51
     Monfieur
    -0.51
    ăng
    -0.50
    emplares
    -0.50
    BufferException
    -0.49
    MemoryWarning
    -0.49
    TagHelpers
    -0.49
    POSITIVE LOGITS
     developers
    0.81
     lenker
    0.76
     developer
    0.75
    Developers
    0.74
     Developers
    0.73
     Developer
    0.65
     виправивши
    0.64
    tanleria
    0.63
    developer
    0.63
     devs
    0.63
    Activations Density 3.332%

    No Known Activations