© 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. 13714
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, especially the word "I", and words and phrases referring to the past, time, home, and personal sentiments

    oai_token-act-pair · 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
     itſelf
    -0.80
     poffible
    -0.72
     ſeveral
    -0.71
     theſe
    -0.70
     becauſe
    -0.69
     unſ
    -0.68
    ſelf
    -0.68
     themſelves
    -0.66
    ^(@)
    -0.66
     fufficient
    -0.66
    POSITIVE LOGITS
    SourceChecksum
    0.60
    GeneratedValue
    0.55
    abstractmethod
    0.55
    انيف
    0.53
     GetEnumerator
    0.53
     Савезне
    0.52
     Had
    0.51
     Ever
    0.50
    awtextra
    0.50
     Disagree
    0.50
    Activations Density 4.687%

    No Known Activations