© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13756
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of".

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    piac
    -0.53
    migrationBuilder
    -0.49
    modelBuilder
    -0.48
     Unidas
    -0.48
     ISNI
    -0.47
    awaiter
    -0.47
    opress
    -0.46
    ADVERTISEMENT
    -0.45
    IsMutable
    -0.43
    tlement
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.80
     ModelExpression
    0.66
     يتيمه
    0.64
    MessageOf
    0.64
    ніципалі
    0.64
     noDo
    0.63
    SBATCH
    0.60
    hasMoreElements
    0.59
    Vidite
    0.58
     Preferencias
    0.58
    Activations Density 0.645%

    No Known Activations