© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8921
    Prev
    Next
    INDEX
    Explanations

    descriptive terms in erotic or sexual contexts, particularly relating to bodies and touch

    oai_token-act-pair · gemini-2.0-flash

    bodies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     initComponents
    -0.72
    fromnode
    -0.68
    انيف
    -0.62
    RenderAtEndOf
    -0.61
    SequentialGroup
    -0.61
     OMITBAD
    -0.61
    decer
    -0.59
     مشين
    -0.59
     chiff
    -0.58
     surla
    -0.58
    POSITIVE LOGITS
     bel
    1.18
    bel
    0.77
    Bel
    0.75
     Bel
    0.74
     BEL
    0.60
     tum
    0.60
    BEL
    0.59
     pal
    0.56
     bla
    0.53
     بيها
    0.48
    Activations Density 3.346%

    No Known Activations