© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6513
    Prev
    Next
    INDEX
    Explanations

    the word "graduated" (or variations of it) and mentions of degrees.

    oai_token-act-pair · gemini-2.0-flash

    graduated

    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
     Италијани
    -0.74
    ervlak
    -0.54
    inSlope
    -0.54
    HasAnnotation
    -0.52
    Enllaços
    -0.51
     незавершена
    -0.50
     أعلام
    -0.50
    Demografie
    -0.50
     Corintios
    -0.50
    Errorf
    -0.49
    POSITIVE LOGITS
     debout
    0.73
     intégr
    0.71
    putExtra
    0.71
     morire
    0.65
    ]")]
    0.65
    /**
    0.64
    principalColumn
    0.64
     veille
    0.63
     recev
    0.63
    TestingModule
    0.63
    Activations Density 1.709%

    No Known Activations