© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10980
    Prev
    Next
    INDEX
    Explanations

    dots in a sequence, possibly representing a file path or class name

    oai_token-act-pair · gemini-2.0-flash

    . or /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    liminaries
    -0.47
     Work
    -0.47
    cautionary
    -0.44
    værk
    -0.42
    ousand
    -0.41
     vendeurs
    -0.41
    learned
    -0.41
    proposed
    -0.40
    milch
    -0.40
    endola
    -0.40
    POSITIVE LOGITS
    
    0.65
    ErrUnexpectedEOF
    0.62
    RectangleBorder
    0.58
     defaultstate
    0.56
     NUKAT
    0.56
    .",
    0.56
     Obrador
    0.56
     Audiodateien
    0.53
     חיצוניים
    0.52
    帖最后由
    0.52
    Activations Density 0.252%

    No Known Activations