© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13165
    Prev
    Next
    INDEX
    Explanations

    positive sentiment attributed to an action, like a scoring play

    oai_token-act-pair · gemini-2.0-flash

    reference to significant sports events or achievements

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

    basketball shooting

    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
    tagHelperRunner
    -0.52
     beginnetje
    -0.50
    migrationBuilder
    -0.49
    EClass
    -0.47
    mergeFrom
    -0.47
     Braxton
    -0.46
    spyOn
    -0.46
    ecap
    -0.45
     kaarangay
    -0.44
     Stellung
    -0.44
    POSITIVE LOGITS
     مرئيه
    0.82
    fjspx
    0.61
     становника
    0.59
     CanadaChoose
    0.58
    alleros
    0.56
    AddTagHelper
    0.55
    AddHtmlAttribute
    0.54
    ientôt
    0.54
     autorytatywna
    0.54
    enment
    0.53
    Activations Density 0.542%

    No Known Activations