© 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. 6786
    Prev
    Next
    INDEX
    Explanations

    references to figures and equations, specifically in scientific writing

    oai_token-act-pair · gemini-2.0-flash

    Image smoothing kernels

    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
    uxxxx
    -0.59
     surla
    -0.50
    ędziesz
    -0.49
    ukasz
    -0.47
     Arno
    -0.47
     regrettable
    -0.46
    ramine
    -0.45
    醐
    -0.45
    AccessorTable
    -0.45
    dope
    -0.44
    POSITIVE LOGITS
    MockBean
    0.66
    GeneratedCode
    0.65
    DebuggerStep
    0.59
    UseVisualStyle
    0.57
     protoimpl
    0.56
     doInBackground
    0.56
    featureID
    0.54
    ValueGeneration
    0.54
    ніципа
    0.54
    FET
    0.53
    Activations Density 2.824%

    No Known Activations