© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15930
    Prev
    Next
    INDEX
    Explanations

    colons and semi-colons surrounding words possibly indicating a list

    oai_token-act-pair · gemini-2.0-flash

    code and technical writing

    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
    Whilst
    -0.60
    semibold
    -0.54
     dedans
    -0.52
     Whilst
    -0.51
     disini
    -0.48
     didalam
    -0.48
    SPECTION
    -0.48
    StartCoroutine
    -0.48
    devamını
    -0.46
     strtok
    -0.46
    POSITIVE LOGITS
    الحياه
    0.84
     nahilalakip
    0.71
     Latch
    0.67
     nakalista
    0.66
    PerformLayout
    0.65
    KommentareTeilen
    0.65
    ValueStyle
    0.65
     оригіналу
    0.63
     :
    0.63
    Besos
    0.63
    Activations Density 3.652%

    No Known Activations