© 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. 10220
    Prev
    Next
    INDEX
    Explanations

    words relating to computer data management and file types

    oai_token-act-pair · gemini-2.0-flash

    scientific and medical texts

    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
     Meta
    -1.86
    Meta
    -1.76
     meta
    -1.75
     MET
    -1.72
     META
    -1.67
    MET
    -1.59
     Met
    -1.59
    meta
    -1.59
     MEL
    -1.56
     Mel
    -1.55
    POSITIVE LOGITS
    InsertCommand
    0.55
    ListModule
    0.47
     Bianchi
    0.47
     HasFactory
    0.45
     Haram
    0.45
     Fuj
    0.44
     NDA
    0.44
     Sai
    0.43
     Ak
    0.43
     Vå
    0.42
    Activations Density 2.040%

    No Known Activations