© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1975
    Prev
    Next
    INDEX
    Explanations

    medical language relating to mental disorders

    oai_token-act-pair · gemini-2.0-flash

    formatting markers and punctuation

    np_token-act-pair-logits · gpt-4o-mini

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     myſelf
    -2.25
     itſelf
    -2.25
     purpoſe
    -2.02
     Efq
    -1.97
     Jefus
    -1.97
     themſelves
    -1.95
     Monfieur
    -1.94
     pleaſure
    -1.91
    ſelf
    -1.90
     auffi
    -1.88
    POSITIVE LOGITS
     
    1.23
     (
    1.13
    ↵
    1.05
     T
    1.02
     B
    1.02
     "
    1.00
     N
    0.98
     '
    0.97
     m
    0.96
     C
    0.95
    Activations Density 40.150%

    No Known Activations