© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11265
    Prev
    Next
    INDEX
    Explanations

    instances of someone trying to achieve or obtain something.

    oai_token-act-pair · gemini-2.0-flash

    get

    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
    IntoConstraints
    -0.56
    aarrggbb
    -0.54
    ies
    -0.52
    AnchorStyles
    -0.52
     autorytatywna
    -0.51
    liosis
    -0.50
    ist
    -0.50
    ides
    -0.50
     BorderSide
    -0.49
    ids
    -0.49
    POSITIVE LOGITS
    $_['
    0.51
     المعيارى
    0.50
     hold
    0.49
    ::_('
    0.49
    #
    0.48
     cereal
    0.46
    itename
    0.45
    pertino
    0.44
     XNUMX
    0.43
    pattern
    0.43
    Activations Density 12.066%

    No Known Activations