© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3766
    Prev
    Next
    INDEX
    Explanations

    positively-charged words related to the world and to impacting lives

    oai_token-act-pair · gemini-2.0-flash

    related to improvement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ValueStyle
    -0.85
    Personendaten
    -0.63
    KommentareTeilen
    -0.63
     transfieras
    -0.63
    __*/
    -0.60
    TagMode
    -0.58
    #+#
    -0.57
     držav
    -0.57
    typeorm
    -0.56
    FontOfSize
    -0.56
    POSITIVE LOGITS
     better
    1.18
     Better
    1.09
    Better
    1.03
    better
    0.99
     kasarigan
    0.91
     stronger
    0.83
     BETTER
    0.82
     richer
    0.80
     melhor
    0.77
     besser
    0.76
    Activations Density 1.638%

    No Known Activations