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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5451
    Prev
    Next
    INDEX
    Explanations

    fragments of explicit sexual descriptions

    oai_token-act-pair · gemini-2.0-flash

    pronouns referring to males

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

    his/him

    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
     jej
    -0.80
     Jej
    -0.79
     její
    -0.77
     her
    -0.74
     she
    -0.72
     &=&
    -0.72
    her
    -0.66
     verla
    -0.66
    &=&\
    -0.64
    &=&
    -0.63
    POSITIVE LOGITS
     his
    2.92
     him
    2.45
    his
    2.33
    彼の
    2.30
     he
    2.30
     himself
    2.25
    彼は
    2.19
    彼が
    2.17
    himself
    1.97
     seiner
    1.93
    Activations Density 6.811%

    No Known Activations