© 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. 52
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing a job well done in addition to the word best, with a secondary association for some political references

    oai_token-act-pair · 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
    SourceChecksum
    -0.58
     незавершена
    -0.55
    UnusedPrivate
    -0.54
    aarrggbb
    -0.51
    CloseOperation
    -0.50
    rostis
    -0.48
    WaitGroup
    -0.48
     auk
    -0.48
     aDecoder
    -0.47
    <bos>
    -0.46
    POSITIVE LOGITS
    μως
    0.67
     do
    0.65
    do
    0.58
     Thron
    0.55
    timg
    0.54
     illustrate
    0.54
    feas
    0.54
     pleaſure
    0.53
     imitation
    0.52
     iconFacebook
    0.52
    Activations Density 10.117%

    No Known Activations