© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12554
    Prev
    Next
    INDEX
    Explanations

    references to cardmaking and blogging activities, often including dates, crafting products, and personal updates.

    oai_token-act-pair · gemini-2.0-flash

    blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     generalised
    -0.79
    COLOUR
    -0.78
     recognised
    -0.69
     standardised
    -0.68
    initialise
    -0.66
     localisation
    -0.66
     anaemia
    -0.66
    neighbours
    -0.66
     coloured
    -0.65
     fertiliser
    -0.65
    POSITIVE LOGITS
    AndEndTag
    0.66
    AxisAlignment
    0.65
     arşivlendi
    0.64
    DockStyle
    0.60
    :].
    0.57
     fiber
    0.54
    MigrationBuilder
    0.54
     []).
    0.54
    幸いです
    0.53
    ({});
    0.52
    Activations Density 9.271%

    No Known Activations