© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6017
    Prev
    Next
    INDEX
    Explanations

    seem to activate common words such as "and", "the", and "to"

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    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
     Partagez
    -0.51
    byr
    -0.48
    builtin
    -0.48
    proof
    -0.45
    呼ば
    -0.44
     membrane
    -0.44
     sì
    -0.43
     and
    -0.43
     Efq
    -0.42
     Proof
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.89
     مشين
    0.81
    principalColumn
    0.80
    BeginContext
    0.80
    évaluateur
    0.78
     propOrder
    0.77
    ConstraintMaker
    0.75
    UserScript
    0.72
    RenderAtEndOf
    0.72
     beginnetje
    0.70
    Activations Density 11.967%

    No Known Activations