© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13669
    Prev
    Next
    INDEX
    Explanations

    text from foreign languages, specifically Croatian and related languages

    oai_token-act-pair · gemini-2.0-flash

    Web page text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ValueStyle
    -0.95
    Hochspringen
    -0.90
     MainAxisSize
    -0.84
     betweenstory
    -0.84
     NSCoder
    -0.82
    .*")]
    -0.82
     purpoſe
    -0.82
    archiviato
    -0.82
    GraphicsUnit
    -0.81
    PickerController
    -0.80
    POSITIVE LOGITS
    אר
    0.41
     im
    0.37
     pré
    0.34
    berkeley
    0.33
     B
    0.33
    als
    0.33
     du
    0.32
    出した
    0.32
     par
    0.32
     l
    0.31
    Activations Density 0.160%

    No Known Activations