© 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. 2145
    Prev
    Next
    INDEX
    Explanations

    various pronouns and helping verbs

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "have"

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

    Forms of "have"

    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
     AssemblyCulture
    -0.72
    +#+#
    -0.60
    LElement
    -0.56
    mybatisplus
    -0.55
    UVWXYZ
    -0.54
    ⓧ
    -0.54
     pinulongan
    -0.54
    ArrowToggle
    -0.54
    neux
    -0.53
    ScopeManager
    -0.52
    POSITIVE LOGITS
     had
    1.17
     having
    1.17
    Have
    1.15
     Have
    1.13
     have
    1.11
    having
    1.09
    have
    1.05
    Having
    1.05
     có
    1.02
    Had
    1.02
    Activations Density 2.414%

    No Known Activations