© 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. 13154
    Prev
    Next
    INDEX
    Explanations

    indicators of tense or time, including past and future

    oai_token-act-pair · gemini-2.0-flash

    French text

    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
     not
    -1.48
    not
    -1.08
     Not
    -1.01
    Not
    -1.00
     anything
    -0.91
     NOT
    -0.91
     nicht
    -0.91
     не
    -0.91
     não
    -0.90
     niet
    -0.86
    POSITIVE LOGITS
    sizeCache
    0.89
     للمعارف
    0.84
     تانيه
    0.84
    TintMode
    0.81
    DockStyle
    0.81
    StoryboardSegue
    0.80
     continúas
    0.80
    ysław
    0.80
    StructEnd
    0.78
    ContentAsync
    0.75
    Activations Density 0.443%

    No Known Activations