© 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. 6223
    Prev
    Next
    INDEX
    Explanations

    the word "I" and language around planning banquets, social events and conferences

    oai_token-act-pair · gemini-2.0-flash

    technical terms and jargon

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

    Attending events

    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
     attendee
    -1.89
     attendees
    -1.87
     event
    -1.80
     attend
    -1.69
     attending
    -1.68
     Event
    -1.66
     evento
    -1.63
     attended
    -1.59
     Attend
    -1.59
    event
    -1.55
    POSITIVE LOGITS
     createSlice
    0.53
    MediaStore
    0.47
    őbb
    0.47
    endpush
    0.43
    Cordialement
    0.42
    izophren
    0.41
    itoriale
    0.40
    JdbcTemplate
    0.40
    веси
    0.40
     CURIAM
    0.40
    Activations Density 0.556%

    No Known Activations