© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11605
    Prev
    Next
    INDEX
    Explanations

    text from dating profiles and legal documents

    oai_token-act-pair · gemini-2.0-flash

    sexual content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     sexual
    -2.19
     Sexual
    -2.16
     Sex
    -2.05
    Sexual
    -2.03
     sex
    -2.02
     sexually
    -2.00
     SEX
    -1.99
    Sex
    -1.93
    sexual
    -1.92
    sex
    -1.80
    POSITIVE LOGITS
    findpost
    0.49
     escuchadas
    0.47
     Layton
    0.43
    Platform
    0.42
    Engine
    0.42
    phyllum
    0.42
     ब्रेकडाउन
    0.42
    ADEM
    0.41
    ricio
    0.41
    wenye
    0.41
    Activations Density 2.655%

    No Known Activations