© 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. 12552
    Prev
    Next
    INDEX
    Explanations

    negative numbers and parenthetical expressions with percentages or references

    oai_token-act-pair · gemini-2.0-flash

    code/math/references

    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
     might
    -2.44
    might
    -2.19
    Might
    -2.03
     Might
    -2.02
     MIGHT
    -1.53
     may
    -1.31
    may
    -1.03
     mungkin
    -1.00
     potrebbe
    -0.90
     misschien
    -0.89
    POSITIVE LOGITS
    ниципа
    0.52
    #![
    0.49
    талья
    0.46
    >((
    0.46
    سبة
    0.43
    NameInMap
    0.43
    Rüyada
    0.42
    ContentAlignment
    0.42
    SBATCH
    0.42
    يكب
    0.41
    Activations Density 2.024%

    No Known Activations