© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7623
    Prev
    Next
    INDEX
    Explanations

    instances of possibility in the text

    oai_token-act-pair · gemini-2.0-flash

    considered

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     يتيمه
    -0.79
    principalTable
    -0.72
     שוליים
    -0.70
    SuppressLint
    -0.66
     should
    -0.66
    should
    -0.65
    Should
    -0.65
     könnt
    -0.64
    setVerticalGroup
    -0.63
    таратура
    -0.62
    POSITIVE LOGITS
     considered
    0.89
     Considered
    0.72
     regarded
    0.69
    considered
    0.68
     considerado
    0.65
     deemed
    0.65
     consideran
    0.65
     considerato
    0.61
     consid
    0.58
     considerados
    0.58
    Activations Density 2.182%

    No Known Activations