© 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. 11548
    Prev
    Next
    INDEX
    Explanations

    words or phrases in Croatian related to Facebook privacy settings and account information.

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    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
     which
    -1.33
     that
    -1.21
    which
    -1.05
     WHICH
    -0.98
     Which
    -0.91
    Which
    -0.86
    that
    -0.85
    hich
    -0.78
     wich
    -0.68
     که
    -0.67
    POSITIVE LOGITS
    enough
    0.48
    SequentialGroup
    0.47
    bonucle
    0.47
     Enough
    0.47
     dus
    0.45
    abras
    0.45
    paksa
    0.44
    TargetApi
    0.43
    linspace
    0.43
    rawtypes
    0.43
    Activations Density 0.520%

    No Known Activations