© 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. 15082
    Prev
    Next
    INDEX
    Explanations

    instances of "a wide" or "an adjective"

    oai_token-act-pair · gemini-2.0-flash

    terms related to wide offerings or selections

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

    wide

    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
     للمعارف
    -0.71
    MigrationBuilder
    -0.59
     autorytatywna
    -0.57
    afficheront
    -0.54
     tỏ
    -0.51
    webElementXpaths
    -0.48
    残
    -0.48
    ➟
    -0.47
     crois
    -0.46
    相当
    -0.45
    POSITIVE LOGITS
     فريبيس
    0.56
    jaro
    0.54
    roxene
    0.54
    HostException
    0.53
    matchCondition
    0.53
    lierung
    0.53
     Factbook
    0.52
    ETHING
    0.52
    ترنت
    0.51
    antity
    0.50
    Activations Density 0.753%

    No Known Activations