© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8517
    Prev
    Next
    INDEX
    Explanations

    the prefix "en"

    oai_token-act-pair · gemini-2.0-flash

    en

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Signalez
    -0.67
    onAttach
    -0.66
    Personendaten
    -0.64
    تقاوى
    -0.63
     Himo
    -0.57
     Italijani
    -0.57
     مشين
    -0.56
     estekak
    -0.56
    новниш
    -0.56
    saraba
    -0.55
    POSITIVE LOGITS
     imageNamed
    0.54
    providedIn
    0.52
    forChild
    0.49
    valently
    0.48
    PTI
    0.46
     getClass
    0.45
    slack
    0.45
    branche
    0.44
    aab
    0.44
    ЧИТА
    0.44
    Activations Density 1.459%

    No Known Activations