© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2934
    Prev
    Next
    INDEX
    Explanations

    mentions of Allah, along with other religious references and a German word

    oai_token-act-pair · gemini-2.0-flash

    Multiple 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
    èdia
    -0.59
    pulumi
    -0.55
    ällor
    -0.55
    getSystemService
    -0.54
     Bioaccumulative
    -0.52
     אות
    -0.52
     DbType
    -0.52
    omock
    -0.51
    ParallelGroup
    -0.51
    ]--;
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.69
    EDEFAULT
    0.64
    AccessorTable
    0.64
    ImageContext
    0.59
     JADX
    0.58
    +:+
    0.56
     doInBackground
    0.52
     continúas
    0.51
     FAM
    0.50
     krijgt
    0.47
    Activations Density 0.155%

    No Known Activations