© 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. 982
    Prev
    Next
    INDEX
    Explanations

    Spanish words and abbreviations, especially pertaining to news and media.

    oai_token-act-pair · gemini-2.0-flash

    del/el

    np_max-act-logits · gemini-2.0-flash

    Spanish articles

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Personensuche
    -0.72
    CopyWith
    -0.69
    Personendaten
    -0.68
    GEBURTSDATUM
    -0.65
     dAtA
    -0.59
    ыгана
    -0.59
     memoized
    -0.57
     Wicidata
    -0.55
    ChildScrollView
    -0.55
    قایناقلار
    -0.53
    POSITIVE LOGITS
    '][]
    0.52
    YTICAL
    0.46
     miracle
    0.46
     disfr
    0.45
    ьа
    0.45
    Método
    0.45
    рованного
    0.44
    ⌓
    0.44
     ModelExpression
    0.44
     büy
    0.44
    Activations Density 0.781%

    No Known Activations