© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9096
    Prev
    Next
    INDEX
    Explanations

    the use of the verb "to be" in different forms, in particular including linking verbs.

    oai_token-act-pair · gemini-2.0-flash

    forms of "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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     sahiptir
    -0.50
     зака
    -0.47
    ullan
    -0.45
    Say
    -0.43
     -
    -0.43
     Say
    -0.43
    gebn
    -0.42
    say
    -0.41
    一番
    -0.40
    より
    -0.40
    POSITIVE LOGITS
     Roskov
    1.06
    DockStyle
    0.89
    sidemargin
    0.82
    Хьажоргаш
    0.81
    BeginContext
    0.78
    RenderAtEndOf
    0.77
     resourceCulture
    0.76
     GoogleFonts
    0.74
     يتيمه
    0.73
    ernalia
    0.73
    Activations Density 3.381%

    No Known Activations