© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10528
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to Spanish festivals and holidays

    oai_token-act-pair · gemini-2.0-flash

    Christian holidays

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    htub
    -0.58
    CloseOperation
    -0.57
     InputDecoration
    -0.55
    enderror
    -0.54
     survie
    -0.52
    modb
    -0.51
    lotl
    -0.50
     Dirk
    -0.50
    iblichen
    -0.50
    مصادر
    -0.49
    POSITIVE LOGITS
     Good
    1.04
     Palm
    0.94
    Good
    0.92
     Ash
    0.82
    Palm
    0.81
     Mau
    0.75
    abestanden
    0.71
     palms
    0.71
    ⓧ
    0.70
     palm
    0.69
    Activations Density 1.388%

    No Known Activations