© 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. 10223
    Prev
    Next
    INDEX
    Explanations

    words that describe locations and structures

    oai_token-act-pair · gemini-2.0-flash

    Houses and properties

    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
    UrlResolution
    -0.78
    principalColumn
    -0.68
     للمعارف
    -0.68
    تقاوى
    -0.68
    цездатний
    -0.59
    URLException
    -0.58
    WriteLiteral
    -0.56
    Према
    -0.55
     jsPsych
    -0.55
    cetamol
    -0.54
    POSITIVE LOGITS
     intptr
    0.58
    vora
    0.52
     LEYENDO
    0.50
     виправивши
    0.50
    sbericht
    0.49
    itamente
    0.48
     aceptas
    0.47
    viewtopic
    0.47
    mailto
    0.46
    Detected
    0.46
    Activations Density 2.744%

    No Known Activations