© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    words related to a specific time or condition and connect those to surroundings of people and objects and morality

    oai_token-act-pair · gemini-2.0-flash

    discussions and legal texts

    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
    ClientRect
    -0.66
    Sucesor
    -0.62
    بوابة
    -0.60
    BASELINE
    -0.59
    ADVERTISEMENT
    -0.58
     Kowalski
    -0.56
    bootstrapcdn
    -0.56
    ardians
    -0.55
    opan
    -0.52
     createState
    -0.52
    POSITIVE LOGITS
     AssemblyCulture
    0.55
    leb
    0.54
    LookAnd
    0.51
    esModule
    0.50
     HasFactory
    0.50
    getFrom
    0.49
     celebrar
    0.47
    ags
    0.47
    γγ
    0.46
    enfance
    0.46
    Activations Density 6.579%

    No Known Activations