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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11371
    Prev
    Next
    INDEX
    Explanations

    explicit and sexual language, particularly describing acts and body parts

    oai_token-act-pair · gemini-2.0-flash

    sexually explicit 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     continúas
    -0.59
    Tē
    -0.49
    ləş
    -0.43
    cstdlib
    -0.42
    InitStruct
    -0.42
     d
    -0.41
     SCD
    -0.41
     heutige
    -0.41
     AssemblyTitle
    -0.41
    hésite
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.83
     him
    0.81
     his
    0.74
     nakalista
    0.69
     InputDecoration
    0.65
    mybatisplus
    0.65
    FailureListener
    0.63
     fieldNum
    0.58
    devamını
    0.58
    digm
    0.57
    Activations Density 17.601%

    No Known Activations