© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10551
    Prev
    Next
    INDEX
    Explanations

    language of research studies, especially statistics

    oai_token-act-pair · gemini-2.0-flash

    Study and data reporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     nonatomic
    -0.50
    ukone
    -0.44
     frå
    -0.44
    Linq
    -0.41
     Landes
    -0.40
    稲田
    -0.40
     säga
    -0.39
     pegatina
    -0.39
     témoins
    -0.38
    ategorised
    -0.38
    POSITIVE LOGITS
     ComVisible
    0.86
     about
    0.77
     Efq
    0.74
     only
    0.73
     BoxDecoration
    0.73
    PositiveButton
    0.69
     Diſ
    0.69
     fevere
    0.68
    zzleHttp
    0.68
    MethodManager
    0.68
    Activations Density 8.818%

    No Known Activations