© 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. 8355
    Prev
    Next
    INDEX
    Explanations

    several common Spanish articles, prepositions, and conjunctions

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    LookAnd
    -0.73
    awtextra
    -0.59
    Personendaten
    -0.53
    utnik
    -0.53
    RenderAtEndOf
    -0.52
     насељу
    -0.52
     nakalista
    -0.48
     contextLoads
    -0.48
    UnsafeEnabled
    -0.48
    expandindo
    -0.48
    POSITIVE LOGITS
    onAttach
    0.55
     serez
    0.54
     onSave
    0.53
     pourrez
    0.52
     maît
    0.50
    zeug
    0.49
    licant
    0.48
    sible
    0.48
    baomidou
    0.47
    ramienta
    0.47
    Activations Density 0.786%

    No Known Activations