© 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. 1326
    Prev
    Next
    INDEX
    Explanations

    inconsistently, code blocks, markup/formatting and some English words.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     in
    -1.98
    ใน
    -1.09
    in
    -1.07
     dalam
    -1.06
     в
    -1.02
     في
    -0.94
     în
    -0.89
     trong
    -0.89
    在
    -0.85
     در
    -0.81
    POSITIVE LOGITS
    !("{
    0.59
    cciale
    0.56
     GetEnumerator
    0.51
    !("{}",
    0.51
    akyti
    0.48
    AddWithValue
    0.47
    ætter
    0.46
    closePath
    0.44
     οποία
    0.44
     "\(
    0.44
    Activations Density 5.459%

    No Known Activations