© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 908
    Prev
    Next
    INDEX
    Explanations

    language fragments with the prefix "sub-" or "anti-" as well as some other random fragments

    oai_token-act-pair · gemini-2.0-flash

    partial words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     étoient
    -1.22
     avoient
    -1.21
     feroit
    -1.10
     fermés
    -1.09
     étoit
    -1.09
     auroit
    -1.06
     stället
    -1.05
     varandra
    -1.05
     igång
    -1.04
     pouvoit
    -1.02
    POSITIVE LOGITS
     tem
    0.59
     cad
    0.57
     _
    0.57
     ra
    0.56
     di
    0.54
     sai
    0.54
     si
    0.54
     reg
    0.54
     kad
    0.53
     câ
    0.52
    Activations Density 3.022%

    No Known Activations