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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12431
    Prev
    Next
    INDEX
    Explanations

    Croatian language text, particularly related to Facebook, errors, and email

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
    тьяна
    -0.53
    UnusedPrivate
    -0.48
     Envío
    -0.47
     Kuba
    -0.47
    Itoa
    -0.47
    rawDesc
    -0.46
    StreetMap
    -0.46
     Aws
    -0.45
     ElementRef
    -0.45
    IMPORTED
    -0.45
    POSITIVE LOGITS
    الإنجليزية
    0.74
     végétale
    0.64
     publiques
    0.60
     médicale
    0.57
    تفصیلات
    0.57
     grecque
    0.57
    IActionResult
    0.56
     présidenti
    0.55
    AddTagHelper
    0.53
    AndEndTag
    0.52
    Activations Density 0.595%

    No Known Activations