© 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. 7118
    Prev
    Next
    INDEX
    Explanations

    the word "bull"

    oai_token-act-pair · gemini-2.0-flash

    the word 'bull'

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

    bull

    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
    cticut
    -0.52
    vidad
    -0.44
    τζ
    -0.43
    zon
    -0.42
     record
    -0.40
     Describes
    -0.40
     Truman
    -0.39
     POSTAGE
    -0.39
    ian
    -0.39
    mazione
    -0.39
    POSITIVE LOGITS
    Geplaatst
    0.77
    WriteBarrier
    0.72
     INTERESAR
    0.60
    εια
    0.56
    queryInterface
    0.54
     Ebers
    0.54
    település
    0.54
    帖最后由
    0.54
    webElementGuid
    0.53
    labus
    0.53
    Activations Density 0.557%

    No Known Activations