© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15486
    Prev
    Next
    INDEX
    Explanations

    words suggesting parsing or separation, often including the word "separate".

    oai_token-act-pair · gemini-2.0-flash

    separate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     separation
    -1.11
     Separation
    -1.08
    Separation
    -1.04
     separating
    -1.00
    separation
    -0.97
     separated
    -0.96
     séparation
    -0.94
     SEPAR
    -0.92
    separ
    -0.91
     separación
    -0.91
    POSITIVE LOGITS
    isfile
    0.48
    InitVars
    0.47
     гла
    0.47
    preventDefault
    0.46
    obby
    0.45
    ูป
    0.44
    calciatore
    0.44
     useCallback
    0.44
     lean
    0.43
    toire
    0.43
    Activations Density 43.018%

    No Known Activations