© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3818
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, especially in the context of travel or physical forces

    oai_token-act-pair · gemini-2.0-flash

    Mechanical and structural elements

    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
     ComVisible
    -0.53
    TargetException
    -0.51
    ofire
    -0.50
     blit
    -0.49
     Linton
    -0.49
     doInBackground
    -0.49
    !*\
    -0.48
    PickerController
    -0.45
    pflege
    -0.44
    AndPassword
    -0.44
    POSITIVE LOGITS
     تانيه
    0.64
     ModelExpression
    0.60
     anchor
    0.58
     Anch
    0.58
    Geplaatst
    0.57
    
    0.55
     autorytatywna
    0.54
    addComponent
    0.54
    Descriere
    0.54
     anchors
    0.52
    Activations Density 1.148%

    No Known Activations