© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15685
    Prev
    Next
    INDEX
    Explanations

    words related to legal and/or business proceedings and medical or personal conditions

    oai_token-act-pair · gemini-2.0-flash

    was will

    np_max-act · gemini-2.0-flash

    starts with w

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    water
    -1.09
    was
    -1.06
    were
    -0.98
    will
    -0.94
    well
    -0.94
    waters
    -0.91
    way
    -0.89
    word
    -0.86
    we
    -0.85
    words
    -0.83
    POSITIVE LOGITS
     W
    0.82
     w
    0.78
     we
    0.64
     wa
    0.57
     wz
    0.55
     WF
    0.54
    arXiv
    0.54
     ws
    0.54
     wi
    0.53
     vi
    0.53
    Activations Density 3.687%

    No Known Activations