© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11982
    Prev
    Next
    INDEX
    Explanations

    discussions of morality, often in a religious context

    oai_token-act-pair · gemini-2.0-flash

    fixing errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     noten
    -0.51
    DoNot
    -0.47
     drills
    -0.45
     devin
    -0.44
    ltä
    -0.44
    %。
    -0.43
    labelledby
    -0.41
     protoimpl
    -0.41
    thique
    -0.41
    formance
    -0.40
    POSITIVE LOGITS
    WithIOException
    0.74
     مرئيه
    0.72
    moveToFirst
    0.71
    GEBURTSDATUM
    0.71
     صوتيه
    0.70
    CppCodeGen
    0.70
     виправивши
    0.69
     GenerationType
    0.69
     Савезне
    0.67
    contentLoaded
    0.66
    Activations Density 0.931%

    No Known Activations