© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    code snippets and words in spanish or portuguese

    oai_token-act-pair · gemini-2.0-flash

    multilingual context

    np_max-act-logits · gemini-2.0-flash

    de

    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
    uxxxx
    -0.64
    WriteTagHelper
    -0.64
    jectures
    -0.63
    rungsseite
    -0.60
    UnusedPrivate
    -0.57
    énario
    -0.56
    EDEFAULT
    -0.55
     dry
    -0.54
     beginnetje
    -0.54
    ectoria
    -0.52
    POSITIVE LOGITS
     quæ
    0.61
     salmón
    0.59
     espagne
    0.58
     saveiro
    0.57
    "}")
    0.55
     unicórnio
    0.54
     zoude
    0.54
     cauſe
    0.53
     esmeralda
    0.53
     fieltro
    0.52
    Activations Density 0.538%

    No Known Activations