© 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. 5685
    Prev
    Next
    INDEX
    Explanations

    phrases describing social activities or functions

    oai_token-act-pair · gemini-2.0-flash

    mentions of social events

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

    event

    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
     '\\;'
    -0.70
     ::=
    -0.54
    Personensuche
    -0.51
     tantôt
    -0.49
     inilah
    -0.47
     endforeach
    -0.47
    conj
    -0.46
     Knud
    -0.45
    byr
    -0.45
     împ
    -0.45
    POSITIVE LOGITS
     event
    1.53
    event
    1.33
     Event
    1.13
    Event
    1.13
     function
    1.09
     events
    1.09
     EVENT
    1.06
     evento
    0.97
     Events
    0.97
     événement
    0.94
    Activations Density 0.876%

    No Known Activations