© 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. 11318
    Prev
    Next
    INDEX
    Explanations

    instances of the word "do" along with references to the fictional substance "spooge".

    oai_token-act-pair · gemini-2.0-flash

    suffixes related to "spo"

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

    spo

    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
     ISNI
    -0.60
     mxArray
    -0.55
    AsUp
    -0.52
     calendriers
    -0.52
     sarili
    -0.50
    CreateModel
    -0.50
     Tune
    -0.49
     bezeichneter
    -0.49
     transfieras
    -0.48
     nonUne
    -0.48
    POSITIVE LOGITS
    oly
    0.69
    ot
    0.68
    otin
    0.66
    ony
    0.66
    od
    0.64
    omin
    0.64
    ons
    0.63
    oni
    0.63
    om
    0.62
    ors
    0.62
    Activations Density 0.868%

    No Known Activations