© 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. 6195
    Prev
    Next
    INDEX
    Explanations

    Java code syntax, especially related to object properties and assignment

    oai_token-act-pair · gemini-2.0-flash

    say "this"

    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
     this
    -2.39
     these
    -1.88
     This
    -1.73
     THIS
    -1.41
    This
    -1.41
     These
    -1.34
     này
    -1.32
     این
    -1.25
     questo
    -1.24
     questa
    -1.24
    POSITIVE LOGITS
    GraphicsUnit
    0.61
    SequentialGroup
    0.58
    uxxxx
    0.55
    tha
    0.52
     NgModule
    0.49
    ther
    0.49
     radiador
    0.49
    owel
    0.49
    AnimationsModule
    0.48
    Etimo
    0.47
    Activations Density 2.776%

    No Known Activations