© 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. 11346
    Prev
    Next
    INDEX
    Explanations

    the word "Little"

    oai_token-act-pair · gemini-2.0-flash

    Little

    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
    matchCondition
    -0.64
     AttributeSet
    -0.64
     femininas
    -0.61
     espirituales
    -0.60
     varandra
    -0.60
     للاسماء
    -0.59
     giusti
    -0.56
     StringTokenizer
    -0.56
    håll
    -0.55
     extérieures
    -0.55
    POSITIVE LOGITS
    multer
    0.59
    epam
    0.54
     [*]
    0.54
     tal
    0.51
     pass
    0.50
    ]<=
    0.50
    umbang
    0.50
    lapp
    0.49
    cloudf
    0.49
    [](
    0.49
    Activations Density 0.885%

    No Known Activations