© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10995
    Prev
    Next
    INDEX
    Explanations

    mentions of eating establishments and the act of dining.

    oai_token-act-pair · gemini-2.0-flash

    restaurants and places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     alimentaires
    -0.61
    帖最后由
    -0.60
     εφ
    -0.60
     pubblici
    -0.60
     sogni
    -0.60
     parlant
    -0.59
     morire
    -0.58
     CURLOPT
    -0.57
     confé
    -0.56
    Nib
    -0.55
    POSITIVE LOGITS
    VolleyError
    0.58
     SQLAlchemy
    0.51
    RegressionTest
    0.50
    }'.
    0.50
     CreateTagHelper
    0.50
    }".
    0.48
    Campeonato
    0.48
     Atm
    0.48
     place
    0.48
    uil
    0.45
    Activations Density 1.786%

    No Known Activations