© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9782
    Prev
    Next
    INDEX
    Explanations

    code snippets, possibly Javascript, including function definitions

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    IsContent
    -0.59
     مشين
    -0.59
     صوتيه
    -0.57
     препратки
    -0.55
     podjela
    -0.52
    Thin
    -0.51
     fonction
    -0.49
    Aholisi
    -0.48
     FUNCTION
    -0.48
    ########.
    -0.48
    POSITIVE LOGITS
     محفوظة
    0.67
     stoi
    0.60
     on
    0.59
    PDOException
    0.57
    SuppressMessage
    0.56
     ['$
    0.54
     QString
    0.53
     NSMutable
    0.51
    featureID
    0.51
    getCurrentUser
    0.49
    Activations Density 2.557%

    No Known Activations