© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9994
    Prev
    Next
    INDEX
    Explanations

    the roots of plants

    oai_token-act-pair · gemini-2.0-flash

    roots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     roots
    -2.08
     Roots
    -1.63
    roots
    -1.59
    Roots
    -1.52
     raíces
    -1.42
     racines
    -1.32
     Wurzeln
    -1.26
     root
    -1.08
     raí
    -1.01
    rooted
    -0.93
    POSITIVE LOGITS
     stället
    0.72
    __':
    0.68
     LIRE
    0.65
     öppna
    0.65
     đãi
    0.63
     transfieras
    0.62
     كومونز
    0.59
     connexes
    0.59
    Geplaatst
    0.58
     egne
    0.58
    Activations Density 1.664%

    No Known Activations