© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9176
    Prev
    Next
    INDEX
    Explanations

    words about providing guidance or help to people

    oai_token-act-pair · gemini-2.0-flash

    needing/providing help and support

    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
    assisted
    -0.67
    Assisted
    -0.67
     Assisted
    -0.64
    mybatisplus
    -0.63
     Assistance
    -0.61
     Guided
    -0.59
    ValueStyle
    -0.58
    Assistance
    -0.57
     assisted
    -0.57
     Assist
    -0.56
    POSITIVE LOGITS
     otomatig
    0.59
    مصادر
    0.53
     ISNI
    0.51
    Referencie
    0.50
    PMailer
    0.49
     évêque
    0.47
    kháu
    0.46
     Emits
    0.46
    antaranya
    0.46
    ๆ
    0.46
    Activations Density 2.773%

    No Known Activations