© 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. 8737
    Prev
    Next
    INDEX
    Explanations

    the word "is" or word fragments starting with "is"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'Is'

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

    Is

    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
    Portale
    -0.58
    </tfoot>
    -0.52
     initComponents
    -0.52
    huber
    -0.49
    hdessä
    -0.48
    enol
    -0.45
    colgroup
    -0.44
     كومونز
    -0.44
    Referències
    -0.43
    DidLoad
    -0.43
    POSITIVE LOGITS
    adaptiveStyles
    0.52
     nakalista
    0.51
    NewUrlParser
    0.51
    ImageContext
    0.51
    Hentet
    0.50
    \{\\
    0.50
    ეთ
    0.50
    ByVersion
    0.49
    TypedDataSet
    0.49
     bēr
    0.49
    Activations Density 0.666%

    No Known Activations