© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9654
    Prev
    Next
    INDEX
    Explanations

    words related to people being instructed or starting careers

    oai_token-act-pair · gemini-2.0-flash

    Woman's experiences

    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
     his
    -2.06
     she
    -1.85
    his
    -1.83
     their
    -1.80
     its
    -1.75
    their
    -1.73
     ihrer
    -1.69
     She
    -1.62
    His
    -1.59
    Their
    -1.59
    POSITIVE LOGITS
     he
    0.46
    __((
    0.44
     لينك
    0.43
    tigas
    0.43
    OptionsMenu
    0.43
    layah
    0.42
    HomeAsUpEnabled
    0.42
    TypedValue
    0.41
    amoja
    0.41
    lelő
    0.41
    Activations Density 2.086%

    No Known Activations