© 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. 7451
    Prev
    Next
    INDEX
    Explanations

    words relating to power, speed, and engines

    oai_token-act-pair · gemini-2.0-flash

    terms related to maximum and minimum values

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

    maximum

    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
    AndEndTag
    -0.88
     الرياضيه
    -0.77
    tagHelperRunner
    -0.75
    Composable
    -0.71
    Jereo
    -0.68
    StoryboardSegue
    -0.68
    Gambas
    -0.66
    AnchorStyles
    -0.65
     насељу
    -0.64
    पया
    -0.64
    POSITIVE LOGITS
     top
    0.88
     max
    0.78
     maximum
    0.76
    top
    0.75
     Top
    0.69
     min
    0.69
    Top
    0.67
    max
    0.66
     topp
    0.61
     minimum
    0.61
    Activations Density 1.337%

    No Known Activations