© 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. 9559
    Prev
    Next
    INDEX
    Explanations

    the word "capital", locations, and names of politicians

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · 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
    eradish
    -0.71
    SharedCtor
    -0.68
     nargin
    -0.66
    ulemon
    -0.63
    resizingMask
    -0.63
     mergeFrom
    -0.62
    terase
    -0.62
    ConstraintMaker
    -0.61
    Tikang
    -0.59
     Winaray
    -0.59
    POSITIVE LOGITS
    memberOf
    0.66
     flag
    0.64
    flag
    0.60
    Flag
    0.55
     Flag
    0.52
     Flags
    0.51
     sah
    0.51
     flags
    0.49
     continúas
    0.49
    poy
    0.49
    Activations Density 1.307%

    No Known Activations