© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2882
    Prev
    Next
    INDEX
    Explanations

    technical language relating to medical procedures

    oai_token-act-pair · gemini-2.0-flash

    Medical procedures

    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
     autorytatywna
    -0.47
    #+#
    -0.45
    arh
    -0.45
    rshire
    -0.43
    syms
    -0.41
     sympy
    -0.41
     препратки
    -0.40
    ril
    -0.40
    WebControls
    -0.40
    żd
    -0.39
    POSITIVE LOGITS
    +#+#
    0.77
     AssemblyCulture
    0.71
    TextWatcher
    0.69
    UnusedPrivate
    0.68
     تضيفلها
    0.67
    bcryptjs
    0.66
    ConstraintMaker
    0.66
    xase
    0.63
    UIControlState
    0.63
     <=",
    0.63
    Activations Density 6.356%

    No Known Activations