© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15306
    Prev
    Next
    INDEX
    Explanations

    technical writing, particularly where equations, experiments, and results could be detailed

    oai_token-act-pair · gemini-2.0-flash

    Describing observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    UnsafeEnabled
    -0.77
    RenderAtEndOf
    -0.69
     Jefus
    -0.65
     varandra
    -0.65
    RectangleBorder
    -0.63
    onAttach
    -0.63
     Majefty
    -0.62
     myſelf
    -0.62
     MyBatis
    -0.62
     leaſt
    -0.62
    POSITIVE LOGITS
    Alike
    0.50
    Дереккөздер
    0.49
    semb
    0.48
     Roskov
    0.47
     pass
    0.47
    passing
    0.46
    тора
    0.46
     Ser
    0.45
    ங்கு
    0.45
     ser
    0.45
    Activations Density 23.052%

    No Known Activations