© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7468
    Prev
    Next
    INDEX
    Explanations

    code snippets in programming questions and answers

    oai_token-act-pair · gemini-2.0-flash

    technical terms and error messages

    np_token-act-pair-logits · gpt-4o-mini

    Code/technical Q&A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    itness
    -0.41
     asking
    -0.39
     giving
    -0.38
     I
    -0.38
    AddTagHelper
    -0.36
     calendriers
    -0.35
    anda
    -0.35
    zulegen
    -0.35
     wishing
    -0.34
     we
    -0.34
    POSITIVE LOGITS
    MemoryWarning
    0.78
    AndEndTag
    0.71
     referrerpolicy
    0.70
     ivelany
    0.68
     AssemblyTitle
    0.66
     IndexError
    0.65
     IBOutlet
    0.65
    :+:
    0.61
    Życiorys
    0.60
    UserScript
    0.60
    Activations Density 7.344%

    No Known Activations