© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13085
    Prev
    Next
    INDEX
    Explanations

    words and characters in languages that are not english

    oai_token-act-pair · gemini-2.0-flash

    Spanish/Portuguese

    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
    jdt
    -0.54
    ⓧ
    -0.54
    glBindTexture
    -0.52
     '\\;'
    -0.50
    mtd
    -0.48
    SourceChecksum
    -0.47
    ïde
    -0.47
     jadx
    -0.47
    getDoctrine
    -0.46
     détaillée
    -0.46
    POSITIVE LOGITS
     CURIAM
    0.58
    lujah
    0.57
    complexType
    0.56
    contentLoaded
    0.56
    ngOnInit
    0.55
     defaultstate
    0.54
    styleUrls
    0.54
    ViewType
    0.52
     snippetHide
    0.52
    secuencias
    0.49
    Activations Density 0.703%

    No Known Activations