© 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. 12931
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical abuse or force

    oai_token-act-pair · gemini-2.0-flash

    Negative/abusive situations

    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
     المعيارى
    -0.66
     fire
    -0.58
    MethodManager
    -0.56
     traite
    -0.55
    InjectAttribute
    -0.55
    titleMargin
    -0.53
    getMenuInflater
    -0.53
    SharedCtor
    -0.50
    fire
    -0.50
    adpleegd
    -0.49
    POSITIVE LOGITS
    ]--;
    0.68
    TagMode
    0.56
     ISNI
    0.56
    ArgsConstructor
    0.55
     eingesch
    0.54
    ROIT
    0.54
     jadx
    0.51
     JADX
    0.51
    èdia
    0.50
    Сообщение
    0.50
    Activations Density 3.876%

    No Known Activations