© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14426
    Prev
    Next
    INDEX
    Explanations

    tokens that contain the character '/' or it finds the word "balance" or "Italian"

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     springfox
    -0.73
    UrlEncoded
    -0.66
    aspectj
    -0.58
    publicain
    -0.56
     saites
    -0.55
     disambiguazione
    -0.54
    TEMPO
    -0.53
     quitted
    -0.53
    multirow
    -0.52
    AutoScale
    -0.52
    POSITIVE LOGITS
    GOTREF
    0.55
    互联网档案馆
    0.52
    رشف
    0.51
    lotl
    0.49
     Савез
    0.48
    gliche
    0.47
    олові
    0.46
    "]).
    0.45
    __;
    0.45
    ]</
    0.45
    Activations Density 1.259%

    No Known Activations