© 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. 5578
    Prev
    Next
    INDEX
    Explanations

    the ends of sentences and clauses, and words related to writing/publishing.

    oai_token-act-pair · gemini-2.0-flash

    various forms of the word "sound"

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

    punctuation

    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
     well
    -0.83
    well
    -0.76
     Well
    -0.73
    Well
    -0.65
     WELL
    -0.63
     even
    -0.57
     bien
    -0.56
    WELL
    -0.56
    ]")]
    -0.54
     also
    -0.53
    POSITIVE LOGITS
     sounds
    0.72
    sound
    0.71
     Those
    0.67
    Those
    0.66
     Sounds
    0.66
    sounds
    0.65
     SOUND
    0.64
     sound
    0.62
     klingt
    0.62
     Sound
    0.61
    Activations Density 1.593%

    No Known Activations