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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8481
    Prev
    Next
    INDEX
    Explanations

    passages that involve violence

    oai_token-act-pair · gemini-2.0-flash

    violence and pain

    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
     Paglinawan
    -0.68
     noqa
    -0.59
    Par
    -0.55
    High
    -0.55
    Билгалдахарш
    -0.54
     Par
    -0.54
     High
    -0.52
    োগ
    -0.52
     ligiloj
    -0.49
    Left
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.72
    TagMode
    0.65
    MessageTagHelper
    0.65
    messageInfo
    0.55
     goodwill
    0.54
     blue
    0.53
     الدولى
    0.52
    +#+#
    0.52
     يتيمه
    0.51
     chivalry
    0.50
    Activations Density 11.044%

    No Known Activations