© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10508
    Prev
    Next
    INDEX
    Explanations

    the word "dot" ('.')

    oai_token-act-pair · gemini-2.0-flash

    dot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     dot
    -0.70
     nos
    -0.62
     the
    -0.62
     former
    -0.60
     
    -0.58
     “
    -0.57
    洛
    -0.57
     two
    -0.57
     char
    -0.57
     val
    -0.56
    POSITIVE LOGITS
     Réponses
    0.96
     feroit
    0.95
     illustrazione
    0.95
     anún
    0.94
    +#+#
    0.93
    rrggbb
    0.93
     guère
    0.92
    TestingModule
    0.91
     pitié
    0.90
     affari
    0.87
    Activations Density 0.765%

    No Known Activations