© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2210
    Prev
    Next
    INDEX
    Explanations

    the word "this" plus some articles like "the" or "a"

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     particular
    -1.22
    particular
    -1.19
    Particular
    -1.04
     Particular
    -0.90
     PARTICULAR
    -0.68
     particolare
    -0.68
     /^\
    -0.65
    $_['
    -0.63
    PARTIC
    -0.63
    ChildScrollView
    -0.61
    POSITIVE LOGITS
     CreateTagHelper
    0.70
     propOrder
    0.59
     fermés
    0.56
     gradova
    0.54
    Tembelea
    0.53
     démocr
    0.52
     cérami
    0.51
     chrétiens
    0.49
     touristes
    0.49
     africains
    0.47
    Activations Density 5.464%

    No Known Activations