© 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. 4720
    Prev
    Next
    INDEX
    Explanations

    the word "left" within mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    left

    np_max-act · 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
     betweenstory
    -0.78
    esez
    -0.77
    #+#
    -0.72
     oprot
    -0.70
     GoogleFonts
    -0.70
    mtrl
    -0.69
    IRUS
    -0.68
    học
    -0.67
    tvguidetime
    -0.67
    liothèque
    -0.66
    POSITIVE LOGITS
    <bos>
    1.03
     nakalista
    0.57
     calore
    0.43
    JAKARTA
    0.41
     and
    0.41
     to
    0.40
     the
    0.40
    V
    0.39
     is
    0.38
     faccia
    0.38
    Activations Density 0.092%

    No Known Activations