© 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. 6322
    Prev
    Next
    INDEX
    Explanations

    journal article citations

    oai_token-act-pair · gemini-2.0-flash

    contractions and possessive forms

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

    archaic pronouns

    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
    hiza
    -0.54
     Normdatei
    -0.52
     års
    -0.50
    îtra
    -0.50
    entuh
    -0.48
    abstractmethod
    -0.47
     mengg
    -0.46
    Provincia
    -0.46
    ésie
    -0.46
    érard
    -0.45
    POSITIVE LOGITS
     myſelf
    0.79
     becauſe
    0.74
     itſelf
    0.72
    ſelves
    0.70
    Sucesor
    0.69
     Efq
    0.67
     themſelves
    0.66
     whoſe
    0.64
     himſelf
    0.64
     ſta
    0.63
    Activations Density 2.465%

    No Known Activations