© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14079
    Prev
    Next
    INDEX
    Explanations

    instances of something "followed" by something else or "unable" to do something

    oai_token-act-pair · gemini-2.0-flash

    followed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    kháu
    -0.65
     quelcon
    -0.60
    enderror
    -0.59
    vician
    -0.58
     незавершена
    -0.57
     Meksiku
    -0.56
    AddHtmlAttribute
    -0.56
     oprot
    -0.56
     électroniques
    -0.55
     vectorielle
    -0.54
    POSITIVE LOGITS
     my
    1.38
    my
    1.02
     mijn
    0.92
    My
    0.83
     My
    0.83
     meine
    0.82
     myself
    0.82
    我的
    0.81
     MY
    0.79
    By
    0.76
    Activations Density 2.358%

    No Known Activations