© 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. 5800
    Prev
    Next
    INDEX
    Explanations

    the word "hard"

    oai_token-act-pair · gemini-2.0-flash

    work and effort

    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
     
    -0.60
    N
    -0.55
    M
    -0.49
    V
    -0.49
     M
    -0.47
    ,
    -0.47
     https
    -0.47
     work
    -0.47
    X
    -0.46
     res
    -0.46
    POSITIVE LOGITS
    expandindo
    1.17
     Monfieur
    0.93
     Efq
    0.85
    发表于
    0.85
    ſelf
    0.84
    sizeCache
    0.83
     disambiguazione
    0.82
    principalColumn
    0.80
     Baillargeon
    0.80
     Theſe
    0.79
    Activations Density 0.501%

    No Known Activations