© 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. 13709
    Prev
    Next
    INDEX
    Explanations

    the word "happy" followed by something, sometimes a holiday or a word starting with 'a'

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "happy"

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

    happy

    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
     uſed
    -0.77
     myſelf
    -0.75
     itſelf
    -0.68
     leaſt
    -0.67
     poffible
    -0.65
     faſt
    -0.64
     chofe
    -0.64
     reaſon
    -0.64
     tranſ
    -0.63
     purpoſe
    -0.62
    POSITIVE LOGITS
     فريبيس
    0.82
    prende
    0.53
    openhauer
    0.51
    esModule
    0.48
     magasiner
    0.47
    flexGrow
    0.46
    MENAFN
    0.46
    ਖ
    0.46
    jupiter
    0.45
     Chwiliwch
    0.45
    Activations Density 0.746%

    No Known Activations