© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15405
    Prev
    Next
    INDEX
    Explanations

    the letter "h" in code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     المعيارى
    -0.99
    GEBURTSDATUM
    -0.94
    aarrggbb
    -0.89
     Мексичка
    -0.82
    }}],
    -0.82
     HasFactory
    -0.78
     onAnimation
    -0.78
     виправивши
    -0.78
    contentLoaded
    -0.77
    IntoConstraints
    -0.77
    POSITIVE LOGITS
     eccl
    0.54
     victimes
    0.52
     aina
    0.47
     altid
    0.45
    нибудь
    0.45
     suelen
    0.45
     équi
    0.44
     tourne
    0.43
     hjæl
    0.43
     redan
    0.43
    Activations Density 4.202%

    No Known Activations