© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9659
    Prev
    Next
    INDEX
    Explanations

    statements about performing or doing well, or conversely, not doing well, in some endeavor

    oai_token-act-pair · gemini-2.0-flash

    Quality assessment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    CppCodeGen
    -0.58
     ComVisible
    -0.57
    ürnberg
    -0.55
    Jegyzetek
    -0.55
     estekak
    -0.55
    SOUNDBITE
    -0.54
    nodoc
    -0.53
    WebMethod
    -0.52
     незавершена
    -0.52
    lccn
    -0.52
    POSITIVE LOGITS
     poorly
    1.22
     well
    1.18
     badly
    1.11
     excellently
    1.08
     favourably
    1.02
     admirably
    1.01
     favorably
    0.96
    well
    0.95
     dobrze
    0.94
     superbly
    0.93
    Activations Density 0.558%

    No Known Activations