© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5726
    Prev
    Next
    INDEX
    Explanations

    help-seeking language common to online forums

    oai_token-act-pair · gemini-2.0-flash

    discussion forum posts

    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
    saraba
    -0.70
    /-/
    -0.62
     initComponents
    -0.58
    ]")]
    -0.58
    AFFIRMED
    -0.57
    Gambas
    -0.57
     titres
    -0.55
    behaviour
    -0.54
    __.__
    -0.54
    érienne
    -0.53
    POSITIVE LOGITS
     mate
    0.53
     hdi
    0.53
    webElementGuid
    0.51
     USG
    0.50
     arches
    0.50
     mates
    0.49
     polyps
    0.49
     quarries
    0.48
     RIAA
    0.48
     Leve
    0.47
    Activations Density 11.856%

    No Known Activations