© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13249
    Prev
    Next
    INDEX
    Explanations

    auxillary verbs like "be", "is", and "are" when they are being used in a sentence in a particular way (but what that particular way is is not entirely explained by the provided data)

    oai_token-act-pair · gemini-2.0-flash

    open

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AccessorTable
    -0.59
    Obrázky
    -0.45
    ]='\
    -0.44
    estra
    -0.43
    ว
    -0.42
     id
    -0.42
    略
    -0.41
    ignez
    -0.41
    templ
    -0.40
    берг
    -0.40
    POSITIVE LOGITS
     open
    1.93
    Open
    1.63
    open
    1.59
     Open
    1.54
     OPEN
    1.48
     abierto
    1.34
    OPEN
    1.34
     abierta
    1.27
     ouvert
    1.26
     deschis
    1.25
    Activations Density 2.672%

    No Known Activations