© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3782
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to find" and common sentence-ending punctuation.

    oai_token-act-pair · gemini-2.0-flash

    find

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RenderAtEndOf
    -0.54
     externi
    -0.54
     beden
    -0.51
     šķ
    -0.50
    venido
    -0.48
    Race
    -0.47
     OkHttpClient
    -0.46
     vermelhas
    -0.46
     windmill
    -0.45
    rinth
    -0.44
    POSITIVE LOGITS
     it
    0.63
     the
    0.61
     they
    0.60
     great
    0.59
    کد
    0.58
     onCreateView
    0.56
     this
    0.55
     yet
    0.53
     a
    0.53
     those
    0.53
    Activations Density 24.836%

    No Known Activations