© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10302
    Prev
    Next
    INDEX
    Explanations

    variants of the word "pal"

    oai_token-act-pair · gemini-2.0-flash

    pal

    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
     sente
    -0.49
    helen
    -0.48
     Symfony
    -0.43
    formazione
    -0.43
    ObjectContext
    -0.43
    生
    -0.43
    pota
    -0.42
    ับ
    -0.42
     हुए
    -0.41
     claro
    -0.41
    POSITIVE LOGITS
    MessageTagHelper
    0.70
    principalTable
    0.65
    पया
    0.64
    хьтан
    0.64
     <<<<<<<<<<<<<<
    0.61
     gynhyrchwyd
    0.61
    SharedDtor
    0.60
     onPostExecute
    0.59
     endwhile
    0.58
     resourceCulture
    0.58
    Activations Density 0.389%

    No Known Activations