© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6145
    Prev
    Next
    INDEX
    Explanations

    the substrings 'ped', 'linc', 'etape' and 'ride'

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    PRWEB
    -0.52
     empate
    -0.50
    ([]);
    -0.50
     Unmarshal
    -0.49
    ToDecimal
    -0.48
     saucer
    -0.47
    ênero
    -0.46
     praia
    -0.46
    cznych
    -0.45
    тек
    -0.45
    POSITIVE LOGITS
     step
    1.98
     steps
    1.84
    step
    1.80
     Step
    1.79
    Step
    1.77
     Steps
    1.69
    steps
    1.64
     STEP
    1.60
    STEP
    1.58
    Steps
    1.52
    Activations Density 0.434%

    No Known Activations