© 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. 6289
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to desserts.

    oai_token-act-pair · gemini-2.0-flash

    words related to ease and compatibility

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

    easier

    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
    sidemargin
    -0.75
    PerformLayout
    -0.73
    UnusedPrivate
    -0.68
     transfieras
    -0.66
    хьтан
    -0.66
    GEBURTSDATUM
    -0.64
     насељу
    -0.64
    rawDesc
    -0.64
    SharedDtor
    -0.63
    @[+][
    -0.61
    POSITIVE LOGITS
     easier
    0.81
    easier
    0.69
     Easier
    0.67
    Easier
    0.60
     leichter
    0.54
    Compati
    0.50
     COMPAT
    0.49
    Compat
    0.48
    ODA
    0.47
     complic
    0.46
    Activations Density 0.921%

    No Known Activations