© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4255
    Prev
    Next
    INDEX
    Explanations

    a jumble of capitalized words, last names, and locations, perhaps related to data extraction

    oai_token-act-pair · gemini-2.0-flash

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     betweenstory
    -0.89
    DockStyle
    -0.88
    BASEPATH
    -0.69
    EndInit
    -0.69
    Personendaten
    -0.68
    AndEndTag
    -0.67
     CreateTagHelper
    -0.67
     autorytatywna
    -0.66
     مشين
    -0.66
    yntaxException
    -0.65
    POSITIVE LOGITS
     missione
    0.52
     Romains
    0.48
     asesino
    0.47
     scolaires
    0.46
     zijne
    0.45
     desnuda
    0.45
    ülé
    0.45
     gantung
    0.44
     exclusivas
    0.43
     juridiques
    0.43
    Activations Density 2.278%

    No Known Activations