© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7927
    Prev
    Next
    INDEX
    Explanations

    past-participle verbs

    oai_token-act-pair · gemini-2.0-flash

    Past events and observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     taken
    -1.79
    taken
    -1.76
     Taken
    -1.73
     arisen
    -1.70
     eaten
    -1.66
    Taken
    -1.63
     risen
    -1.59
     flown
    -1.57
     TAKEN
    -1.55
     spoken
    -1.55
    POSITIVE LOGITS
     gave
    1.47
     took
    1.30
     saw
    1.19
     did
    1.18
     was
    1.16
     went
    1.13
     came
    1.06
     threw
    1.04
     wrote
    1.03
     showed
    0.96
    Activations Density 0.778%

    No Known Activations