© 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. 9898
    Prev
    Next
    INDEX
    Explanations

    phrases indicating liking, wanting, or caring about something

    oai_token-act-pair · gemini-2.0-flash

    Non-English words

    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
     complete
    -1.25
    complete
    -1.19
     Complete
    -1.07
    Complete
    -1.04
     open
    -1.02
    open
    -0.91
     COMPLETE
    -0.90
     Open
    -0.87
     run
    -0.84
     secure
    -0.83
    POSITIVE LOGITS
     виправивши
    0.59
     naselje
    0.54
    økt
    0.51
     uintptr
    0.51
     enfans
    0.50
     humains
    0.48
    הערות
    0.48
     normaux
    0.47
     Manusia
    0.47
    AndroidJUnit
    0.47
    Activations Density 6.833%

    No Known Activations