© 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. 11593
    Prev
    Next
    INDEX
    Explanations

    instances of people affecting or relating to themselves or each other or things happening against them

    oai_token-act-pair · gemini-2.0-flash

    herself

    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
     pleaſure
    -3.48
     ſche
    -3.45
     itſelf
    -3.42
     Monfieur
    -3.42
     myſelf
    -3.41
     purpoſe
    -3.34
     Majefty
    -3.30
     Shakspeare
    -3.25
     ſtate
    -3.14
     Cæsar
    -3.13
    POSITIVE LOGITS
     
    1.96
     “
    1.95
     ‘
    1.90
     la
    1.88
    ratulations
    1.83
     co
    1.80
     qu
    1.78
     a
    1.77
     «
    1.77
     de
    1.76
    Activations Density 6.312%

    No Known Activations