© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9029
    Prev
    Next
    INDEX
    Explanations

    finite verbs in French

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     period
    -0.42
     Grand
    -0.40
     kind
    -0.40
     volta
    -0.40
    omor
    -0.39
    isa
    -0.39
    typec
    -0.39
    pec
    -0.38
    kind
    -0.38
    يش
    -0.38
    POSITIVE LOGITS
     know
    2.30
     knows
    2.22
    know
    2.20
    Know
    2.20
     Know
    2.16
    KNOW
    2.08
     KNOW
    2.00
    knows
    1.99
     knew
    1.95
     knowing
    1.94
    Activations Density 0.075%

    No Known Activations