© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11105
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that end sentences or clauses and sometimes other seemingly random words

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     but
    -0.56
     Nevertheless
    -0.54
     And
    -0.52
     Nonetheless
    -0.50
    AndEndTag
    -0.50
     nevertheless
    -0.49
     Additionally
    -0.48
     Lastly
    -0.48
    And
    -0.47
     ancak
    -0.47
    POSITIVE LOGITS
    ########.
    0.85
    ")));
    
    0.81
     سكانية
    0.71
     Waray
    0.71
    دانشنامهٔ
    0.68
    
    0.68
    లాలు
    0.68
     ―――――
    0.66
    '))
    
    0.66
    rungsseite
    0.65
    Activations Density 7.579%

    No Known Activations