© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10426
    Prev
    Next
    INDEX
    Explanations

    Russian language code snippets

    oai_token-act-pair · gemini-2.0-flash

    Computer code and languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Cæsar
    -0.82
     Christendom
    -0.52
     Protestantism
    -0.50
     Athene
    -0.49
     Josephus
    -0.46
     NGO
    -0.46
     ZF
    -0.45
     Papal
    -0.45
     Kaf
    -0.45
     colorés
    -0.45
    POSITIVE LOGITS
    awtextra
    0.84
    httphttps
    0.83
    makeConstraints
    0.78
     CreateTagHelper
    0.73
    findpost
    0.70
    UIControlState
    0.69
    SequentialGroup
    0.63
    EDEFAULT
    0.62
    afficheront
    0.62
     snippetHide
    0.62
    Activations Density 1.144%

    No Known Activations