© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5648
    Prev
    Next
    INDEX
    Explanations

    the word "thing" or "things" and also "cloth"

    oai_token-act-pair · gemini-2.0-flash

    thing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ste
    -0.45
    thoven
    -0.45
    ANNES
    -0.43
    thaf
    -0.42
     Guil
    -0.41
    isse
    -0.41
    amo
    -0.41
    land
    -0.40
     adev
    -0.40
    shared
    -0.40
    POSITIVE LOGITS
    httphttps
    0.99
     resourceCulture
    0.78
    Tembelea
    0.73
    #+#
    0.73
    SBATCH
    0.71
    twimg
    0.70
     autorytatywna
    0.69
    VersionUID
    0.69
    adaptiveStyles
    0.66
    abestanden
    0.66
    Activations Density 0.988%

    No Known Activations