© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 183
    Prev
    Next
    INDEX
    Explanations

    a large amount of common and uncommon words

    oai_token-act-pair · gemini-2.0-flash

    don/Don

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Audiodateien
    -0.90
    intios
    -0.80
     initComponents
    -0.72
    MLLoader
    -0.71
    IndentedString
    -0.69
     ***!
    -0.66
     protoimpl
    -0.65
    uxxxx
    -0.61
    __*/
    -0.60
     GetEnumerator
    -0.60
    POSITIVE LOGITS
     don
    2.13
    don
    1.75
    Don
    1.72
     Don
    1.68
    DON
    1.41
     DON
    1.36
    Dont
    1.26
     dont
    1.17
    dont
    1.13
     Dont
    1.07
    Activations Density 3.859%

    No Known Activations