© 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. 5633
    Prev
    Next
    INDEX
    Explanations

    punctuation at the ends of sentences and at the ends of reported speech

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     started
    -1.13
     worked
    -1.09
     went
    -1.07
     happened
    -1.06
     did
    -1.05
     occurred
    -1.05
     responded
    -1.05
     acted
    -1.01
     reached
    -1.01
     began
    -1.00
    POSITIVE LOGITS
     Vorsitzender
    0.55
     tør
    0.54
    onOptions
    0.52
     adicionais
    0.51
     constituencies
    0.51
     ""}
    0.49
     miljø
    0.49
     Biosciences
    0.47
    entera
    0.47
     friv
    0.45
    Activations Density 3.447%

    No Known Activations