© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11351
    Prev
    Next
    INDEX
    Explanations

    the word "can" followed by a verb or the word "be"

    oai_token-act-pair · gemini-2.0-flash

    instances of 'can'

    np_token-act-pair-logits · gpt-4o-mini

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ✭✭
    -0.58
    BufferException
    -0.58
    ocyto
    -0.51
    terase
    -0.51
    anyahu
    -0.49
     Pense
    -0.49
    HasIndex
    -0.48
     ممکن
    -0.48
    のではなく
    -0.48
    ristan
    -0.48
    POSITIVE LOGITS
     InputDecoration
    0.70
     GenerationType
    0.69
     ddelweddau
    0.59
     be
    0.55
     cdti
    0.53
    KURZBESCHREIBUNG
    0.53
    tvguidetime
    0.52
     sounded
    0.50
     terdengar
    0.50
     jScrollPane
    0.50
    Activations Density 0.579%

    No Known Activations