© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15808
    Prev
    Next
    INDEX
    Explanations

    words related to places, especially those in historical contexts.

    oai_token-act-pair · gemini-2.0-flash

    geographical locations and movements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     surla
    -0.71
    withIdentifier
    -0.58
    InputBorder
    -0.52
     isInitialized
    -0.51
    Mam
    -0.51
    Portale
    -0.50
     الرياضيه
    -0.50
     لينك
    -0.50
     Nabi
    -0.50
    SizeF
    -0.50
    POSITIVE LOGITS
     médical
    0.57
     fédé
    0.53
     eccl
    0.50
    rayage
    0.48
    stals
    0.47
    pendenti
    0.47
    intios
    0.46
    acherous
    0.45
     médicaux
    0.45
    locene
    0.45
    Activations Density 1.573%

    No Known Activations