© 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. 15848
    Prev
    Next
    INDEX
    Explanations

    various programming code elements and citation-related abbreviations

    oai_token-act-pair · gemini-2.0-flash

    people

    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
     gradient
    -0.63
     buffer
    -0.63
     contour
    -0.60
     amplification
    -0.60
     surface
    -0.60
     flow
    -0.59
     buffering
    -0.59
     scale
    -0.58
     saturation
    -0.58
     heat
    -0.57
    POSITIVE LOGITS
     friends
    1.00
     friend
    0.94
     students
    0.91
     student
    0.88
     boy
    0.86
     boys
    0.86
     kids
    0.84
     parents
    0.84
     guests
    0.82
     brother
    0.81
    Activations Density 7.600%

    No Known Activations