© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3794
    Prev
    Next
    INDEX
    Explanations

    mathematical questions involving numbers and symbols

    oai_token-act-pair · gemini-2.0-flash

    math problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ViewFeatures
    -1.05
     Roskov
    -0.96
    ".
    -0.96
     >=",
    -0.94
    '):
    -0.94
     Италијани
    -0.94
    ftagPool
    -0.93
    "):
    -0.91
    __":
    -0.91
    клопе
    -0.91
    POSITIVE LOGITS
    Copy
    0.46
    About
    0.43
    a
    0.43
    For
    0.43
    How
    0.42
    Create
    0.41
    about
    0.40
    f
    0.40
    Since
    0.40
    Q
    0.40
    Activations Density 6.401%

    No Known Activations