© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12567
    Prev
    Next
    INDEX
    Explanations

    chunks of code, particularly C++ code, with some focus on SQL and data structures.

    oai_token-act-pair · gemini-2.0-flash

    narrative text

    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
     student
    -1.02
     friends
    -1.00
     friend
    -1.00
     students
    -0.98
     parents
    -0.97
     boys
    -0.94
     family
    -0.94
     employee
    -0.92
     boy
    -0.92
     father
    -0.91
    POSITIVE LOGITS
     ljus
    0.51
     buffer
    0.51
     waveform
    0.51
     contours
    0.51
     contour
    0.51
     flow
    0.51
     gradient
    0.51
     format
    0.50
     amplification
    0.50
     spike
    0.50
    Activations Density 8.104%

    No Known Activations