© 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. 3520
    Prev
    Next
    INDEX
    Explanations

    text about future security threats or new trends

    oai_token-act-pair · gemini-2.0-flash

    only

    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
    ReusableCell
    -0.75
    #+#
    -0.56
    celes
    -0.52
    WithIOException
    -0.47
    とも言
    -0.46
    }{*}{
    -0.45
    はじめに
    -0.44
    ֹא
    -0.43
    ">+
    -0.42
    complexContent
    -0.42
    POSITIVE LOGITS
     only
    2.72
    only
    2.36
    Only
    2.30
     Only
    2.17
    ONLY
    1.90
     ONLY
    1.84
     только
    1.79
     tylko
    1.63
     seulement
    1.63
    только
    1.55
    Activations Density 2.313%

    No Known Activations