© 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. 8454
    Prev
    Next
    INDEX
    Explanations

    words related to reclining chairs and their parts

    oai_token-act-pair · gemini-2.0-flash

    terms related to adjustments or configurations

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

    Seating and chairs

    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
    EndContext
    -0.68
     kaarangay
    -0.65
    twimg
    -0.64
     houſe
    -0.64
     Houſe
    -0.62
     fieldNum
    -0.59
    addCriterion
    -0.58
     ſch
    -0.57
     resourceCulture
    -0.57
    ]--;
    -0.57
    POSITIVE LOGITS
    elif
    0.56
     arm
    0.53
     مشين
    0.52
    ynchro
    0.49
     Miller
    0.49
    miller
    0.48
    میل
    0.47
     instructing
    0.47
    lect
    0.47
    wär
    0.47
    Activations Density 0.766%

    No Known Activations