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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 834
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in conversations related to LGBTQ+ themes or subtext

    oai_token-act-pair · gemini-2.0-flash

    innuendo and subtext

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AndEndTag
    -1.07
     himſelf
    -0.96
     Majefty
    -0.95
     themſelves
    -0.92
     pleaſure
    -0.90
     Jefus
    -0.90
     myſelf
    -0.88
     betweenstory
    -0.86
     Monfieur
    -0.86
     ſever
    -0.84
    POSITIVE LOGITS
     hints
    0.52
     last
    0.41
     hint
    0.40
     hinted
    0.39
     prom
    0.38
    prom
    0.37
     Hints
    0.36
     hinting
    0.36
     statement
    0.35
     cryptic
    0.35
    Activations Density 1.265%

    No Known Activations