© 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. 8539
    Prev
    Next
    INDEX
    Explanations

    SGML/XML-like tags and code snippets.

    oai_token-act-pair · gemini-2.0-flash

    HTML links and references

    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
     levies
    -0.58
     MPR
    -0.57
     Dory
    -0.56
     DSS
    -0.55
    IPR
    -0.54
    IPS
    -0.54
    ders
    -0.54
     TSI
    -0.53
     MDR
    -0.52
     Thessal
    -0.52
    POSITIVE LOGITS
    دانشنامهٔ
    0.66
    berdayakan
    0.64
     démocr
    0.63
     nød
    0.59
     bakgrund
    0.57
     nødven
    0.56
    hidupan
    0.56
     tarko
    0.56
    quién
    0.55
     picioare
    0.55
    Activations Density 14.672%

    No Known Activations