© 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. 14327
    Prev
    Next
    INDEX
    Explanations

    verbs, especially past participles, often related to modification or change

    oai_token-act-pair · gemini-2.0-flash

    words related to recovery and improvement

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

    recovery and relocation

    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
     up
    -1.54
     out
    -1.16
    up
    -1.07
     down
    -1.02
     Up
    -0.87
    Up
    -0.87
     off
    -0.85
     mergeFrom
    -0.75
    down
    -0.75
     UP
    -0.72
    POSITIVE LOGITS
     layui
    0.49
    écnicas
    0.46
    OfWork
    0.45
     itself
    0.45
     themselves
    0.44
     familiale
    0.42
    الحياه
    0.41
     grazia
    0.41
    thodes
    0.40
     extérieures
    0.40
    Activations Density 5.291%

    No Known Activations