Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 9971
    Prev
    Next
    INDEX
    Explanations

    phrases enclosed in quotation marks, and also some punctuation near words indicating aggression

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     themſelves
    -1.12
     himſelf
    -1.11
     myſelf
    -1.05
     purpoſe
    -1.05
     houſe
    -1.04
     pleaſure
    -1.04
     itſelf
    -1.03
     Efq
    -1.00
     AssemblyCulture
    -0.96
     Houſe
    -0.95
    POSITIVE LOGITS
     I
    0.65
     
    0.60
     Be
    0.58
     P
    0.55
     Don
    0.55
     E
    0.54
     me
    0.53
     &
    0.52
     Ben
    0.51
     Per
    0.49
    Activations Density 0.775%

    No Known Activations