© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7186
    Prev
    Next
    INDEX
    Explanations

    code related to editor folding

    oai_token-act-pair · gemini-2.0-flash

    fold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    tadır
    -0.76
    Diweddarwch
    -0.75
     Paglinawan
    -0.73
     tartalomajánló
    -0.70
     Efq
    -0.68
    WillAppear
    -0.68
    msgTypes
    -0.66
    }*/
    -0.65
    ratulations
    -0.65
     iſt
    -0.62
    POSITIVE LOGITS
    TemporalType
    0.50
    ComponentName
    0.49
     tiết
    0.47
    व्य
    0.46
    ütfen
    0.43
    Example
    0.42
     Sheikh
    0.41
     扣
    0.41
    alini
    0.41
    onia
    0.40
    Activations Density 1.984%

    No Known Activations