© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11123
    Prev
    Next
    INDEX
    Explanations

    blank lines

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     EconPapers
    -0.93
     Roskov
    -0.79
     esternos
    -0.77
     المعيارى
    -0.77
    HostException
    -0.76
    ValueStyle
    -0.70
    تقاوى
    -0.69
     defaultstate
    -0.69
     kaarangay
    -0.68
     AssemblyProduct
    -0.68
    POSITIVE LOGITS
     volna
    0.53
    ILayout
    0.45
    طني
    0.45
     setType
    0.43
    erski
    0.42
    幹
    0.42
    agissait
    0.41
    ודם
    0.41
    슛
    0.41
    rano
    0.40
    Activations Density 0.300%

    No Known Activations