© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12921
    Prev
    Next
    INDEX
    Explanations

    the word "put" and words related to physical intervention.

    oai_token-act-pair · gemini-2.0-flash

    put

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     put
    -2.56
    Put
    -2.30
    put
    -2.19
     Put
    -2.17
     PUT
    -1.88
     puts
    -1.86
     putting
    -1.77
    Putting
    -1.72
    PUT
    -1.71
     Putting
    -1.70
    POSITIVE LOGITS
     murales
    0.50
     maestra
    0.50
     richesse
    0.46
    moveToFirst
    0.45
    dfunding
    0.44
     setuptools
    0.44
    řejmě
    0.44
    fattning
    0.43
     manuscrit
    0.43
     ujednoznacz
    0.42
    Activations Density 4.269%

    No Known Activations