© 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. 13501
    Prev
    Next
    INDEX
    Explanations

    java source code blocks plus the word "console"

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     HasFactory
    -0.78
     فريبيس
    -0.68
    IsMutable
    -0.66
    EFIAPI
    -0.63
     CURIAM
    -0.62
    UnsafeEnabled
    -0.61
    SequentialGroup
    -0.61
    godic
    -0.60
     createContext
    -0.60
    minister
    -0.60
    POSITIVE LOGITS
    <bos>
    0.82
    AddField
    0.45
    MessageTagHelper
    0.44
     benne
    0.39
    MLLoader
    0.38
     notizia
    0.37
    ↵↵
    0.35
    neté
    0.33
    antaranya
    0.33
     Hauteur
    0.33
    Activations Density 0.383%

    No Known Activations