© 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. 1517
    Prev
    Next
    INDEX
    Explanations

    the contraction "'d" preceded by various pronouns.

    oai_token-act-pair · 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
     hadn
    -1.07
     had
    -1.05
    Had
    -0.95
     Had
    -0.93
    had
    -0.86
     habían
    -0.82
     avaient
    -0.75
    HAD
    -0.74
     HAD
    -0.73
     Monfieur
    -0.71
    POSITIVE LOGITS
    RefNanny
    0.59
    migrationBuilder
    0.57
    UseVisualStyle
    0.52
    IntoConstraints
    0.52
     ^=
    0.49
    bnf
    0.47
     betweenstory
    0.47
    SBATCH
    0.47
     —
    0.46
     createSlice
    0.45
    Activations Density 0.945%

    No Known Activations