© 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. 15999
    Prev
    Next
    INDEX
    Explanations

    a variety of different words related to computer code, grammar, the verb "to be", and literature

    oai_token-act-pair · gemini-2.0-flash

    non-english words

    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
     Said
    -0.61
    FILED
    -0.56
    ACHED
    -0.56
     Fed
    -0.56
    Felt
    -0.55
     gada
    -0.54
    IED
    -0.54
     felt
    -0.54
     Loved
    -0.54
     looked
    -0.53
    POSITIVE LOGITS
    ImageContext
    0.63
     giebt
    0.60
    :][
    0.59
     organisée
    0.59
    WebElementEntity
    0.59
     normaux
    0.58
    specie
    0.58
     CreateTagHelper
    0.58
     Italijanski
    0.57
     terminée
    0.57
    Activations Density 3.495%

    No Known Activations