© 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. 6245
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs indicating possibility

    oai_token-act-pair · gemini-2.0-flash

    words indicating existence or action in passive voice

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

    capabilities

    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
     found
    -0.77
     pleaſure
    -0.77
     Found
    -0.73
    found
    -0.73
    find
    -0.71
    Saw
    -0.69
    usehen
    -0.66
     find
    -0.66
     ſtate
    -0.65
    ⓧ
    -0.65
    POSITIVE LOGITS
     was
    0.90
     được
    0.88
    被
    0.88
     werd
    0.81
    也被
    0.81
     wurde
    0.77
     been
    0.77
    又被
    0.76
     wurden
    0.72
     být
    0.72
    Activations Density 1.935%

    No Known Activations