© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10629
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating infrequency or rarity

    oai_token-act-pair · gemini-2.0-flash

    something rare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Scribd
    -0.61
    regado
    -0.54
     ioutil
    -0.52
    Atoi
    -0.52
     strconv
    -0.51
    Divide
    -0.49
    ibra
    -0.48
     damit
    -0.45
     vọng
    -0.45
    melidir
    -0.44
    POSITIVE LOGITS
    windowFixed
    0.57
    Спасылкі
    0.56
     насељу
    0.55
     rare
    0.55
    Література
    0.55
     Guel
    0.53
    encodeWith
    0.52
     fortun
    0.52
     saites
    0.52
    IsMutable
    0.51
    Activations Density 0.701%

    No Known Activations