© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13523
    Prev
    Next
    INDEX
    Explanations

    lines beginning with "#" (often used for titles) followed by the word "Running" or lines containing "--" (often used for flags)

    oai_token-act-pair · gemini-2.0-flash

    --

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     --
    -2.22
    --
    -2.00
    )--
    -1.53
    "--
    -1.48
    '--
    -1.42
     "--
    -1.40
    ---
    -1.37
    --"
    -1.37
    .--
    -1.32
     ---
    -1.30
    POSITIVE LOGITS
    „
    0.97
     „
    0.89
     XNUMX
    0.76
    \{\\
    0.69
     〈
    0.67
     \%$\\
    0.67
    Brainz
    0.66
    ՚
    0.65
     „,
    0.63
    AndroidJUnit
    0.63
    Activations Density 1.431%

    No Known Activations