© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4683
    Prev
    Next
    INDEX
    Explanations

    biological and political walls between entities.

    oai_token-act-pair · gemini-2.0-flash

    barrier/wall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    estacks
    -0.67
    GRANTED
    -0.66
    rinology
    -0.60
    ErrorListener
    -0.60
    EDEFAULT
    -0.60
     createSlice
    -0.60
     jadx
    -0.58
    onViewCreated
    -0.58
    eynman
    -0.57
     فريبيس
    -0.56
    POSITIVE LOGITS
     barrier
    1.16
     barriers
    1.13
     wall
    1.00
     walls
    0.98
     Barriers
    0.96
    Barriers
    0.96
    wall
    0.95
    barrier
    0.94
     Barrier
    0.93
    walls
    0.85
    Activations Density 1.774%

    No Known Activations