© 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. 13605
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, especially forms of "to be" like "is", "was", and "being", in the passive voice and other verb phrases.

    oai_token-act-pair · gemini-2.0-flash

    "to be"

    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
     Grüsse
    -0.60
    mación
    -0.59
    invokeLater
    -0.56
    ISMS
    -0.56
     light
    -0.56
    Going
    -0.54
    glTexCoord
    -0.54
    Legături
    -0.53
    rencies
    -0.53
    going
    -0.52
    POSITIVE LOGITS
    ">//
    0.74
     VIAF
    0.56
    VIAF
    0.54
    存于互联网档案馆
    0.52
     acting
    0.51
    fromnode
    0.49
    MarshalTo
    0.49
    Mucho
    0.47
    σια
    0.47
    éndole
    0.46
    Activations Density 2.508%

    No Known Activations