Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14525
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives expressing some sort of evaluation or judgment

    oai_token-act-pair · gemini-2.0-flash

    ok

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     voici
    -0.63
    iastes
    -0.62
     courir
    -0.56
    ArgsConstructor
    -0.54
    (&:
    -0.54
     plastiques
    -0.54
     endblock
    -0.54
    lccn
    -0.54
     Parcelable
    -0.53
     especiais
    -0.52
    POSITIVE LOGITS
     ok
    0.81
     OK
    0.75
     dec
    0.74
     alright
    0.70
     Ok
    0.67
     OKAY
    0.66
     okay
    0.65
    AsUp
    0.65
    JspWriter
    0.62
    Ok
    0.61
    Activations Density 2.252%

    No Known Activations